Papers with translation
Touch Editing: A Flexible One-Time Interaction Approach for Translation (2020.aacl-main)
Copied to clipboard
| Challenge: | Existing methods for machine translation require intensive keyboard interaction, which is inconvenient on mobile devices. |
| Approach: | They propose a touch-based editing method that is more flexible than keyboard-mouse-based translation postediting. |
| Outcome: | The proposed method significantly outperforms existing interactive translation methods on translation datasets and on post-editing datasets. |
Multilingual Neural Machine Translation (2020.coling-tutorials)
Copied to clipboard
| Challenge: | In this tutorial, we will cover the latest advances in NMT to enhance low-resource translation. |
| Approach: | They will cover the latest advances in NMT approaches that leverage multilingualism . they will focus on topics such as language divergence, transfer learning and pivoting . |
| Outcome: | This tutorial will cover the latest advances in NMT to enhance low-resource translation models. |
DeepTrans: Deep Reasoning Translation via Reinforcement Learning (2026.tacl-1)
Copied to clipboard
| Challenge: | Recent studies have shown promising performance in various downstream tasks. |
| Approach: | They propose a deep reasoning translation model that learns free translation via reinforcement learning (RL) they build a reward model with pre-defined scoring criteria on the translation results and thought processes . |
| Outcome: | The proposed model outperforms strong deep reasoning LLMs in literature translation and outperformed other models. |
TransIns: Document Translation with Markup Reinsertion (2021.emnlp-demo)
Copied to clipboard
| Challenge: | MT models cannot translate complex formatted documents, as markup can be nested, apply to spans contiguous in source but non-contiguous. |
| Approach: | They propose a system for non-plain text document translation that reinserts markup into translated sentences using token alignments between source and target sentences. |
| Outcome: | The proposed system outperforms translation services in terms of markup quality . it integrates token alignments between source and target sentences to reinsert markup . the proposed system is available under the MIT license . |
Difficulty-Aware Machine Translation Evaluation (2021.acl-short)
Copied to clipboard
| Challenge: | Current MT evaluation measures pay the same attention to each sentence component . in real-world examinations, the questions vary in difficulty and weightings . |
| Approach: | They propose a difficulty-aware MT evaluation metric that takes translation difficulty into account . they propose to use this metric to evaluate machine translation (MT) results . |
| Outcome: | The proposed method outperforms most MT evaluation metrics in terms of human correlation. |
Speech-to-Speech Translation with Discrete-Unit-Based Style Transfer (2024.acl-srw)
Copied to clipboard
| Challenge: | Existing methods to translate spoken utterances from one language to another are unable to preserve speaker timbre of source speech. |
| Approach: | They propose a pipeline with style-transfer capability on the basis of self-supervised speech representations and codec units. |
| Outcome: | The proposed model achieves zero-shot cross-lingual style transfer on previously unseen source languages. |
Exploring In-Image Machine Translation with Real-World Background (2025.findings-acl)
Copied to clipboard
| Challenge: | Existing models for IIMT focus on simplified scenarios, which is far from reality and impractical for applications in the real world. |
| Approach: | They propose a model that separates the background and text-image from the source image and performs translation on the text- image directly. |
| Outcome: | The proposed model improves translation quality and visual effect in complex scenarios . it separates background and text-image from source image and performs translation on the text- image directly . |
Simultaneous Translation (2020.emnlp-tutorials)
Copied to clipboard
| Challenge: | Simultaneous translation is a problem that has long been considered one of the hardest problems in AI . this tutorial will provide a deep understanding of the history and the recent advances in simultaneous translation. |
| Approach: | This tutorial will examine the design and evaluation of policies for simultaneous translation . it will provide an overview of the history and recent advances in simultaneous translation. |
| Outcome: | This tutorial will examine the design and evaluation of policies for simultaneous translation . |
Probing Word Translations in the Transformer and Trading Decoder for Encoder Layers (2021.naacl-main)
Copied to clipboard
| Challenge: | Neural Machine Translation (NMT) has attracted wide attention in recent years. |
| Approach: | They propose a probing-based approach to measure word translation accuracy using transformer layers. |
| Outcome: | The proposed model outperforms previous probing-based translation models. |
Tied Multitask Learning for Neural Speech Translation (N18-1)
Copied to clipboard
| Challenge: | Recent efforts in endangered language documentation focus on collecting spoken language resources . BULB project uses mobile app to collect spoken resources accompanied by spoken translations . |
| Approach: | They propose a model where the second task decoder receives information from the first task . they apply regularization that encourages transitivity and invertibility to the model . |
| Outcome: | The proposed model improves performance on low-resource speech transcription and translation tasks. |
Simpson’s Paradox and the Accuracy-Fluency Tradeoff in Translation (2024.acl-short)
Copied to clipboard
| Challenge: | Existing studies suggest that accuracy and fluency should trade off against each other, and that capturing every detail of the source is difficult for human raters to distinguish. |
| Approach: | They propose to evaluate the relationship between accuracy and fluency at the segment level and to use probabilities to estimate probabilities. |
| Outcome: | The proposed model relies on human judgments of accuracy and fluency collected in prior work on translation quality estimation. |
fairseq: A Fast, Extensible Toolkit for Sequence Modeling (N19-4)
Copied to clipboard
Myle Ott, Sergey Edunov, Alexei Baevski, Angela Fan, Sam Gross, Nathan Ng, David Grangier, Michael Auli
| Challenge: | OpenNMT is a community-built toolkit written in multiple languages with an emphasis on extensibility. |
| Approach: | They propose to use PyTorch to train custom sequence models for translation, summarization, language modeling, and other tasks. |
| Outcome: | The proposed toolkit is fast, extensible, and useful for both research and production. |
Empirical Evaluation of Active Learning Techniques for Neural MT (D19-61)
Copied to clipboard
| Challenge: | Several active learning (AL) algorithms for machine translation (MT) have been well-studied for phrase-based MT. |
| Approach: | They propose to use a phrase-based algorithm to compare different AL methods in a simulated AL framework to demonstrate how unsupervised pre-training and paraphrastic embedding can be used to improve existing AL methods. |
| Outcome: | The proposed method outperforms existing methods in the context of phrase-based MT and is based on a simulated phrase-driven dataset. |
Subset Retrieval Nearest Neighbor Machine Translation (2023.acl-long)
Copied to clipboard
| Challenge: | k-nearest-neighbor machine translation (kNN-MT) is a new approach to improve NMT performance without additional training. |
| Approach: | They propose a method that integrates example-search into the decoding algorithm to improve neighbor token retrieval. |
| Outcome: | The proposed method achieves a speed-up of up to 132.2 times and an improvement in BLEU score of up 1.6 compared with kNN-MT in the WMT’19 translation task and the domain adaptation tasks in De-En and En-Ja. |
Multimodal Neural Machine Translation Using Synthetic Images Transformed by Latent Diffusion Model (2023.acl-srw)
Copied to clipboard
| Challenge: | Existing methods to translate source language sentences using images are not optimal for machine translation. |
| Approach: | They propose a new multimodal neural machine translation model using synthetic images transformed by a latent diffusion model. |
| Outcome: | The proposed model improves translation performance on English-German translation tasks using the Multi30k dataset. |
Low-resource neural machine translation with morphological modeling (2024.findings-naacl)
Copied to clipboard
| Challenge: | Existing methods for character-based and sub-word tokenization are limited to the surface forms of the words. |
| Approach: | They propose a framework-solution for modeling complex morphology in low-resource settings using a transformer architecture and beam search-based decoder. |
| Outcome: | The proposed model improves translation performance on Kinyarwanda English translation using public-domain parallel text. |
Document-Level Neural Machine Translation Using BERT as Context Encoder (2020.aacl-srw)
Copied to clipboard
| Challenge: | Large-scale pre-trained representations such as BERT have been widely used in many natural language understanding tasks. |
| Approach: | They propose to use BERT as a context encoder to achieve document-level contextual information, which is then integrated into both the encoder and decoder. |
| Outcome: | The proposed model outperforms strong document-level machine translation baselines on BLEU score and captures document- level context information to boost translation performance. |
Gender bias amplification during Speed-Quality optimization in Neural Machine Translation (2021.acl-short)
Copied to clipboard
| Challenge: | et al., 2002) show that gendered noun translation performance degrades faster than BLEU. |
| Approach: | They propose to use greedy search, quantization, AANs and shallow decoders to speed up decoding . they find minimal degradation of BLEU, but gendered noun translation degrades faster . |
| Outcome: | The proposed model degrades gendered noun translation performance faster than other models. |
Improving the Calibration of Confidence Scores in Text Generation Using the Output Distribution’s Characteristics (2025.acl-short)
Copied to clipboard
| Challenge: | Existing methods for estimating confidence in text generation do not account for many valid answers in generation tasks. |
| Approach: | They propose task-agnostic confidence metrics that rely solely on model probabilities without the need for further fine-tuning or heuristics. |
| Outcome: | The proposed models improve the accuracy of BART and Flan-T5 on summarization, translation, and question answering datasets. |
Opportunities for Human-centered Evaluation of Machine Translation Systems (2022.findings-naacl)
Copied to clipboard
| Challenge: | a new study examines the role of machine translation in larger user-facing systems . a sysadmin and a human factors researcher are developing evaluation tools . |
| Approach: | They argue that machine translation models are embedded in larger user-facing systems . they argue that evaluation at the systems level is still lacking . |
| Outcome: | The proposed model evaluations are based on human-computer interaction models . the authors argue that evaluations should be based more on the entire system . |
VOLIMET: A Parallel Corpus of Literal and Metaphorical Verb-Object Pairs for English–German and English–French (2024.starsem-1)
Copied to clipboard
| Challenge: | Metaphorical language is a complex interplay of cultural and linguistic elements that characterizes metaphorical language . a corpus of parallel sentences containing gold standard alignments of metaphorical verb-object pairs and literal paraphrases is presented . |
| Approach: | They propose to analyze metaphorical verb-object pairs and literal paraphrases in parallel sentences from English to German and French. |
| Outcome: | The proposed corpus of 2,916 parallel sentences reveals monolingual patterns for metaphorical vs. literal uses in English . cross-lingually, the results show a rich variability in translations as well as different behaviors for the two target languages . |
Restricted or Not: A General Training Framework for Neural Machine Translation (2022.acl-srw)
Copied to clipboard
| Challenge: | Existing work imposes constraints on beam search decoding, which limits the concurrent processing ability of the model in deployment. |
| Approach: | They propose a general training framework that allows a model to support both restricted and unrestricted translations by adopting an additional auxiliary training process without constraining the decoding process. |
| Outcome: | The proposed training framework is tested on simulated and original benchmarks. |
Counterfactual Data Augmentation for Neural Machine Translation (2021.naacl-main)
Copied to clipboard
| Challenge: | Neural machine translation models often rely on large-scale parallel corpora for training, exhibiting degraded performance on low-resource languages. |
| Approach: | They propose a method that interprets language models and phrasal alignment causally and generates augmented parallel translation corpora by sampling new source phrases from a masked language model. |
| Outcome: | The proposed method improves translation, backtranslation and translation robustness on IWSLT’15 English Vietnamese, WMT’17 English - German, and WMT'18 English – Turkish. |
Revamping Multilingual Agreement Bidirectionally via Switched Back-translation for Multilingual Neural Machine Translation (2024.findings-eacl)
Copied to clipboard
| Challenge: | Current multilingual agreement (MA) methods require parallel data between multiple language pairs, which is not always realistic and optimize the agreement in an ambiguous direction, which hampers the translation performance. |
| Approach: | They propose a novel multilingual agreement framework that optimizes agreement bidirectionally with the Kullback-Leibler Divergence loss. |
| Outcome: | The proposed method improves strong baselines on the task of multilingual neural machine translation with three benchmarks: TED Talks, News, and Europarl. |
The Effects of Language Token Prefixing for Multilingual Machine Translation (2022.aacl-short)
Copied to clipboard
| Challenge: | In recent years, the field has moved towards large neural models either translating from or into many languages. |
| Approach: | They propose to prefix language tokens onto a source or target sequence to improve translation performance. |
| Outcome: | The proposed methods improve translation performance and source side prefixes improve translation. |
Cultural and Geographical Influences on Image Translatability of Words across Languages (2021.naacl-main)
Copied to clipboard
| Challenge: | Neural machine translation models produce poor translations when there are few/no parallel sentences to train the models. |
| Approach: | They define image translatability as the translability of words as images associated with words in different languages that have a high degree of visual similarity. |
| Outcome: | The proposed model improves upon text-only models only marginally. |
RETURNN as a Generic Flexible Neural Toolkit with Application to Translation and Speech Recognition (P18-4)
Copied to clipboard
| Challenge: | Using RETURNN, we train and decode attention models for translation and speech recognition. |
| Approach: | They propose a layer-wise pretraining scheme for recurrent attention models and show its significant effect on deep recurrence encoder networks. |
| Outcome: | The proposed training and decoding scheme improves 1% on expected training and improves on WMT 2017 and Switchboard. |
Train Once, and Decode As You Like (2020.coling-main)
Copied to clipboard
| Challenge: | Existing approaches to machine translation support autoregressive, semi-autoregressive and refinement-based non-auto-regressives. |
| Approach: | They propose a unified approach for supporting different generation manners of machine translation including autoregressive, semi-autoregressive and refinement-based non-auto-regressives. |
| Outcome: | The proposed approach achieves better or competitive translation performance compared with strong baseline models in all the settings. |
Presentation Slide Translation and Layout Error Correction by LLMs (2026.acl-srw)
Copied to clipboard
| Challenge: | Existing translation tools suffer from layout errors due to text expansion during translation . a new approach to translating Japanese slides into English is proposed to overcome this issue . |
| Approach: | They propose a framework to translate Japanese slides into English and correct layout errors by using multimodal LLMs with slide images and XML structures. |
| Outcome: | The proposed method outperforms baselines and achieves 4.1% layout error rate and over 80% success rate. |
UCSYNLP-Lab Machine Translation Systems for WAT 2019 (D19-52)
Copied to clipboard
| Challenge: | Neural machine translation (NMT) has achieved stateof-the-art performance on various language pairs. |
| Approach: | They describe the UCSYNLP-Lab submission to WAT 2019 for Myanmar-English translation tasks in both directions. |
| Outcome: | The proposed translation system improves the performance of Myanmar-English translation tasks. |
Translate With Care: Addressing Gender Bias, Neutrality, and Reasoning in Large Language Model Translations (2025.findings-acl)
Copied to clipboard
| Challenge: | addressing gender bias and maintaining logical coherence in machine translation remains challenging, especially when translating between natural gender languages, like English, and genderless languages, such as Persian, Indonesian, and Finnish. |
| Approach: | They propose a dataset to assess translation systems' performance in six low- to mid-resource languages and a translation dataset to examine gender bias and logical coherence. |
| Outcome: | The Translate-with-Care dataset, comprising 3,950 challenging scenarios across six low- to mid-resource languages, reveals a universal struggle in translating genderless content, resulting in gender stereotyping and reasoning errors. |
On-device System of Compositional Multi-tasking in Large Language Models (2025.emnlp-industry)
Copied to clipboard
Ondrej Bohdal, Konstantinos Theodosiadis, Asterios Mpatziakas, Dimitrios Filippidis, Iro Spyrou, Christos Zonios, Anastasios Drosou, Dimosthenis Ioannidis, Kyenghun Lee, Jijoong Moon, Hyeonmok Ko, Mete Ozay, Umberto Michieli
| Challenge: | Existing approaches to generative AI for large language models struggle when executing complex tasks simultaneously. |
| Approach: | They propose a novel approach tailored specifically for compositional multi-tasking scenarios . they add a learnable projection layer on top of the combined summarization and translation adapters. |
| Outcome: | The proposed approach performs well and is fast in both cloud-based and on-device implementations. |
Empirical Error Modeling Improves Robustness of Noisy Neural Sequence Labeling (2021.findings-acl)
Copied to clipboard
| Challenge: | Standard sequence labeling systems fail when processing noisy user-generated text or consuming the output of an OCR process. |
| Approach: | They propose an empirical error generation approach that employs a sequence-to-sequence model trained to perform translation from error-free to erroneous text. |
| Outcome: | The proposed method outperforms baseline noise generation and error correction techniques on the erroneous sequence labeling data sets. |
Multilingual Argument Mining: Datasets and Analysis (2020.findings-emnlp)
Copied to clipboard
| Challenge: | Argument mining tasks in non-English languages are dominated by English . we use a pre-trained language model that supports 104 languages to train models . |
| Approach: | They propose a multilingual BERT model to address argument mining tasks in non-English languages . they use English datasets and machine translation to facilitate transfer learning . |
| Outcome: | The proposed model is well suited for classifying the stance of arguments and detecting evidence, but less so for assessing the quality of arguments. |
The OPUS-MT Dashboard – A Toolkit for a Systematic Evaluation of Open Machine Translation Models (2023.acl-demo)
Copied to clipboard
| Challenge: | OPUS-MT dashboard provides a comprehensive overview of open translation models . the landscape of machine translation (MT) is increasingly blurry due to the growing volume of shared tasks and models published within the community. |
| Approach: | OPUS-MT dashboard provides a comprehensive overview of open translation models . dashboard includes summaries of benchmarks for over 2,300 models covering 4,560 languages . authors focus on centralization, reproducibility and coverage of MT evaluation combined with scalability . |
| Outcome: | OPUS-MT dashboard provides a comprehensive overview of open translation models . the evaluation tool includes summaries of benchmarks for over 2,300 models spanning 4,560 languages and 294 languages . |
EvolveMT: an Ensemble MT Engine Improving Itself with Usage Only (2023.acl-industry)
Copied to clipboard
| Challenge: | EvolveMT is a method for the efficient combination of multiple machine translation engines. |
| Approach: | They propose a method that selects the output from one engine for each segment and uses online learning techniques to predict the most appropriate system for each translation request. |
| Outcome: | The proposed method achieves similar translation accuracy at a lower cost than selecting the best translation of each segment from all translations using an MT quality estimator. |
BanglaSTEM: A Parallel Corpus and Term-Weighted Evaluation for Technical Bangla-English Translation (2026.acl-srw)
Copied to clipboard
| Challenge: | Large language models excel at technical problem solving in English but struggle when questions are posed in Bangla. |
| Approach: | They propose a dataset of 5,000 Bangla-English sentence pairs to align technical terms . they use OCR to extract matching passages from bilingual textbooks . |
| Outcome: | The proposed pipeline extracts matching passages from bilingual textbooks and uses them to align sentences and mark technical terms. |
Synchronous Syntactic Attention for Transformer Neural Machine Translation (2021.acl-srw)
Copied to clipboard
| Challenge: | Existing syntaxbased NMT models use monolingual syntactic information on either side or both. |
| Approach: | They propose a mechanism that synchronizes source-side and target-side syntactic self-attentions by minimizing the difference between target- and target side self- attentions mapped by the encoder-decoder attention matrix. |
| Outcome: | The proposed method improves translation performance on WMT14 En-De, WMT16 En-Ro, and ASPEC Ja-En (up to +0.38 points in BLEU). |
Zero-Shot vs. Translation-Based Cross-Lingual Transfer: The Case of Lexical Gaps (2024.naacl-short)
Copied to clipboard
| Challenge: | lexical gaps exist in a variety of domains, such as QA, but they can only be expressed as a combination of words in another language. |
| Approach: | They compare the current performance and long-term viability of two approaches to cross-lingual transfer . they leverage lexical gaps to create a multilingual question answering dataset . |
| Outcome: | The proposed model outperforms zero-shot transfer and machine translation (MT) lexical gaps exist in a variety of domains, including linguistics, linguistic coding, and linguistic analysis. |
Language-Aware Multilingual Machine Translation with Self-Supervised Learning (2023.findings-eacl)
Copied to clipboard
| Challenge: | Multilingual machine translation (MMT) is a challenging multitask optimization problem because of lack of a framework to learn language-specific parameters. |
| Approach: | They propose a self-supervised learning task that denies monolingual data to MMT . they then propose 'intra-distillation' task that co-trains with MMT task . |
| Outcome: | The proposed approach outperforms three state-of-the-art methods on 8-language and 15-language benchmarks. |
FRMT: A Benchmark for Few-Shot Region-Aware Machine Translation (2023.tacl-1)
Copied to clipboard
Parker Riley, Timothy Dozat, Jan A. Botha, Xavier Garcia, Dan Garrette, Jason Riesa, Orhan Firat, Noah Constant
| Challenge: | a new dataset and evaluation benchmark for Few-shot Region-aware Machine Translation is presented . FRMT is a type of style-targeted translation that uses labeled training data to perform tasks. |
| Approach: | They propose a dataset and evaluation benchmark for Few-shot Region-aware Machine Translation. |
| Outcome: | The proposed model is based on two translations from English into Portuguese and Mandarin Chinese. |
Probabilistic Bilingual Subword Segmentation with Latent Subword Alignment (2026.eacl-srw)
Copied to clipboard
| Challenge: | Existing methods do not consider parallel relationships, preventing translation model training. |
| Approach: | They propose a method for learning subword correspondences in parallel sentence pairs using the EM algorithm. |
| Outcome: | The proposed method improves translation accuracy for many tasks. |
Learning to Translate Ambiguous Terminology by Preference Optimization on Post-Edits (2025.emnlp-industry)
Copied to clipboard
| Challenge: | Ambiguous terminology can make translation difficult, especially in corporate contexts. |
| Approach: | They propose to learn how to disambiguate terminology based on human post-edits . they use preference optimization to optimize for correctness using the term post-Edit . |
| Outcome: | The proposed framework improves term accuracy over a translation oriented LLM without significant losses in COMET score. |
Is Encoder-Decoder Redundant for Neural Machine Translation? (2022.aacl-main)
Copied to clipboard
| Challenge: | Encoder-decoder architecture is widely adopted for sequence-to-sequence modeling tasks. |
| Approach: | They propose to combine bilingual and multilingual translations to train a language model to do translation. |
| Outcome: | The proposed approach performs on par with the baseline encoder-decoder Transformer . the proposed approach is compared with the translation model in the target language . |
Aligning Vector-spaces with Noisy Supervised Lexicon (N19-1)
Copied to clipboard
| Challenge: | Current approaches to learning to translate between two vector spaces assume that the lexicon defines alignment pairs is noise-free. |
| Approach: | They propose a model that accounts for noisy pairs and propose supervised learning problems for this problem. |
| Outcome: | The proposed model significantly improves translation accuracy on bilingual word embedding translation and mapping between diachronic embeddable spaces. |
Do Multilingual Language Models Think Better in English? (2024.naacl-short)
Copied to clipboard
| Challenge: | Existing studies show that translation-test improves performance of multilingual models by translating the input into English using an external machine translation system. |
| Approach: | They propose a new approach that leverages the few-shot translation capabilities of multilingual language models. |
| Outcome: | The proposed approach outperforms direct inference on 5 tasks. |
WLASL-LEX: a Dataset for Recognising Phonological Properties in American Sign Language (2022.acl-short)
Copied to clipboard
| Challenge: | Signed Language Processing (SLP) is a major form of NLP, but has been overlooked by the NLP community. |
| Approach: | They leverage existing resources to construct a large-scale dataset of American Sign Language signs annotated with six different phonological properties. |
| Outcome: | The proposed model outperforms existing approaches on signs unobserved during training. |
Compositional Representation of Morphologically-Rich Input for Neural Machine Translation (P18-2)
Copied to clipboard
| Challenge: | Neural machine translation models are typically trained with fixed-size input and output vocabularies, which creates a bottleneck on their accuracy and generalization capability. |
| Approach: | They propose to replace the source-language embedding layer of NMT with a bi-directional recurrent neural network that generates compositional representations of the input at any desired level of granularity. |
| Outcome: | The proposed approach outperforms existing methods in a low-resource setting with five languages . the proposed approach consistently outperformed existing methods with a single word representation . |
Extreme Adaptation for Personalized Neural Machine Translation (P18-2)
Copied to clipboard
| Challenge: | Existing models that capture speaker-related variations do not include explicit information about the speaker. |
| Approach: | They propose a method that adapts the bias of the output softmax to each particular user . they propose to model speaker-related variations as an additional bias vector in the softmax layer . |
| Outcome: | The proposed technique improves translation accuracy and better reflection of speaker traits in target text. |
Learning from Chunk-based Feedback in Neural Machine Translation (P18-2)
Copied to clipboard
| Challenge: | a common problem with explicit ratings of translations is that users are not qualified enough to provide reliable feedback for the whole sentence. |
| Approach: | They propose a way to learn from partial feedback in neural machine translation . they ask users to highlight a correct chunk of a translation based on partial feedback . |
| Outcome: | The proposed method outperforms sentence-based feedback by 2.61% BLEU absolute. |
As Little as Possible, as Much as Necessary: Detecting Over- and Undertranslations with Contrastive Conditioning (2022.acl-short)
Copied to clipboard
| Challenge: | Neural machine translation is susceptible to coverage errors such as the addition of superfluous target words or the omission of important source content. |
| Approach: | They propose a method for detecting Omission and addition errors with off-the-shelf translation models. |
| Outcome: | The proposed method is comparable to a supervised method that requires a custom quality estimation model. |
Normalization of Indonesian-English Code-Mixed Twitter Data (D19-55)
Copied to clipboard
| Challenge: | Twitter is an excellent source of textual data for NLP researches, but it is noisy and often contains typos, slang terms, and non-standard abbreviations. |
| Approach: | They propose a standardization system for Indonesian-English code-mixed Twitter data that includes tokenization, language identification, lexical normalization, and translation. |
| Outcome: | The proposed standardization system is based on four modules for tokenization, language identification, lexical normalization, and translation. |
A Lifelong Multilingual Multi-granularity Semantic Alignment Approach via Maximum Co-occurrence Probability (2024.lrec-main)
Copied to clipboard
| Challenge: | Existing methods to mask and predict tokens in multilingual text limit multilingual interaction . |
| Approach: | They propose a lifelong multilingual multi-granularity semantic alignment approach which continuously extracts massive aligned linguistic units from noisy data via a maximum co-occurrence probability algorithm. |
| Outcome: | The proposed approach improves translation performance on WMT14 18 benchmarks in twelve directions. |
Cross-Lingual Transfer from Related Languages: Treating Low-Resource Maltese as Multilingual Code-Switching (2024.eacl-long)
Copied to clipboard
| Challenge: | Multilingual models exhibit impressive cross-lingual transfer capabilities on unseen languages, but performance is impacted when there is a script disparity with the languages used in the model’s pre-training data. |
| Approach: | They propose a novel method to align a resource-rich language's script with a target language and train a classifier that can make informed decisions regarding the appropriate processing of each token. |
| Outcome: | The proposed model can be used to transfer a language's scripts across multiple languages, but it is suboptimal for mixed languages, where only a subset benefits while the rest is impeded. |
Adapting High-resource NMT Models to Translate Low-resource Related Languages without Parallel Data (2021.acl-long)
Copied to clipboard
Wei-Jen Ko, Ahmed El-Kishky, Adithya Renduchintala, Vishrav Chaudhary, Naman Goyal, Francisco Guzmán, Pascale Fung, Philipp Koehn, Mona Diab
| Challenge: | linguistic overlap between low-resource languages and high-resourced languages is a major obstacle for training high-quality machine translation systems. |
| Approach: | They exploit linguistic overlap to facilitate translation to and from low-resource languages . they use monolingual data and parallel data in related high-resourced languages based on their method . |
| Outcome: | The proposed method significantly improves translation into low-resource language compared to baselines on 7 languages from three different language families. |
DATScore: Evaluating Translation with Data Augmented Translations (2023.findings-eacl)
Copied to clipboard
| Challenge: | Experimental results show that DATScore correlates better with human meta-evaluations than the other recent state-of-the-art metrics. |
| Approach: | They propose to use data augmented translations to improve the evaluation of machine translations by using two new scoring strategies. |
| Outcome: | The proposed metric improves on 3 NLG tasks other than translation. |
LLMs Are Zero-Shot Context-Aware Simultaneous Translators (2024.emnlp-main)
Copied to clipboard
| Challenge: | Existing SiMT systems operate on a sentence level, disregarding the context established by previous sentences or the broader context implied by previous words. |
| Approach: | They show that open-source LLMs perform on par with or better than some state-of-the-art baselines in simultaneous machine translation tasks, zero-shot. |
| Outcome: | The proposed models perform on par with or better than state-of-the-art baselines in simultaneous machine translation tasks, zero-shot. |
Detect, Disambiguate, and Translate: On-Demand Visual Reasoning for Multimodal Machine Translation with Large Vision-Language Models (2025.naacl-long)
Copied to clipboard
Danyang Liu, Fanjie Kong, Xiaohang Sun, Dhruva Patil, Avijit Vajpayee, Zhu Liu, Vimal Bhat, Najmeh Sadoughi
| Challenge: | Multimodal machine translation (MMT) aims to leverage additional modalities beyond text . current MMT systems rely heavily on monolingual English captioning data . |
| Approach: | They propose a reasoning-based framework to leverage large-scale vision-language models for MMT . they propose Detect, Disambiguate, and Translate framework to detect ambiguity in input sentence . |
| Outcome: | The proposed framework outperforms state-of-the-art models in disambiguation accuracy and translation quality. |
Different Speech Translation Models Encode and Translate Speaker Gender Differently (2025.acl-short)
Copied to clipboard
| Challenge: | Recent studies on interpreting the hidden states of speech models have shown their ability to capture speaker-specific features, including gender. |
| Approach: | They propose to use probing methods to assess gender encoding across ST models. |
| Outcome: | The proposed models capture speaker-specific features, including gender, while older models do not . low gender encoding capabilities result in systems’ tendency toward a masculine default, a translation bias that is more pronounced in newer architectures. |
Exploiting Curriculum Learning in Unsupervised Neural Machine Translation (2021.findings-emnlp)
Copied to clipboard
| Challenge: | Experimental results show that the proposed method achieves consistent improvements with faster convergence speed. |
| Approach: | They propose a curriculum learning method to gradually utilize pseudo bi-texts based on their quality from multiple granularities. |
| Outcome: | The proposed method achieves consistent improvements with faster convergence speed on WMT 14 En-Fr, WMT14 En-De, and LDC En-Zh translation tasks. |
Too Late to Train, Too Early To Use? A Study on Necessity and Viability of Low-Resource Bengali LLMs (2025.coling-main)
Copied to clipboard
Tamzeed Mahfuz, Satak Kumar Dey, Ruwad Naswan, Hasnaen Adil, Khondker Salman Sayeed, Haz Sameen Shahgir
| Challenge: | a new generation of English-oriented Large Language Models significantly outperforms older LLMs on low-resource languages. |
| Approach: | They compare Bengali-oriented LLMs with open-weight and closed-source LLM models . they conclude that there is a need for a Bengali model, but lacks high-quality pretraining data . |
| Outcome: | The proposed model outperforms existing models on Bengali on low-resource languages . the results highlight biases in machine-translated datasets used for Bengali NLP tasks . |
One Model to Learn Both: Zero Pronoun Prediction and Translation (D19-1)
Copied to clipboard
| Challenge: | Zero pronouns (ZPs) are often omitted in pro-drop languages, but should be recalled in non-pro-drop language. |
| Approach: | They propose a unified and discourse-aware ZP translation approach for neural MT models . they jointly learn to predict and translate ZPs in an end-to-end manner . |
| Outcome: | The proposed method improves translation performance and ZP prediction accuracy over baseline models and external models. |
Dynamic Past and Future for Neural Machine Translation (D19-1)
Copied to clipboard
| Challenge: | Neural machine translation models can benefit from modeling translated and untranslated source contents as recurrent states, but this less interpretable recurrence hinders their power to model dynamic updating of and contents during decoding. |
| Approach: | They propose to model the dynamic updating of and contents during decoding by explicitly separating source words into groups of translated and untranslated contents through parts-to-wholes assignment. |
| Outcome: | The proposed method achieves significant improvements over both Rnmt and Transformer by producing more adequate translations. |
Deep Generative Model for Joint Alignment and Word Representation (N18-1)
Copied to clipboard
| Challenge: | EmbedAlign model embeds words in their complete observed context and learns by marginalisation of latent lexical alignments. |
| Approach: | They exploit translation as a distributional context and embed words as posterior probability densities, rather than point estimates, which allows them to compare words in context using a measure of overlap between distributions. |
| Outcome: | The proposed model performs on a range of lexical semantics tasks and achieves competitive results on benchmarks including natural language inference, paraphrasing, and text similarity. |
FrugalScore: Learning Cheaper, Lighter and Faster Evaluation Metrics for Automatic Text Generation (2022.acl-long)
Copied to clipboard
| Challenge: | Existing evaluation metrics are not reliable, but require significant computational resources. |
| Approach: | They propose a method to learn a fixed, low cost version of any expensive NLG metric while retaining most of its original performance. |
| Outcome: | The proposed approach retains most of the original performance while running faster and faster. |
Translate to Disambiguate: Zero-shot Multilingual Word Sense Disambiguation with Pretrained Language Models (2024.eacl-long)
Copied to clipboard
| Challenge: | Pretrained language models learn cross-lingual knowledge and perform well on diverse tasks when finetuned. |
| Approach: | They propose a zero-shot prompting approach that captures cross-lingual word sense with a contextual prompt. |
| Outcome: | The proposed approach outperforms baselines on recall in many evaluation languages without additional training or finetuning. |
Cross-lingual Text Classification Transfer: The Case of Ukrainian (2025.coling-main)
Copied to clipboard
| Challenge: | despite the large amount of labeled datasets, there is an imbalance in data availability across languages. |
| Approach: | They explore cross-lingual knowledge transfer methods avoiding manual data curation . they use large multilingual encoders and translation systems, LLMs, and language adapters . |
| Outcome: | The proposed approaches are tested on three text classification tasks in Ukrainian . the authors show that the proposed approaches avoid manual data curation . |
Meet Changes with Constancy: Learning Invariance in Multi-Source Translation (2020.coling-main)
Copied to clipboard
| Challenge: | Existing approaches to multi-source neural machine translation neglect inconsistencies between sources of information. |
| Approach: | They propose a source invariance network to learn invariant information of parallel sources . they propose to integrate such network with multi-encoder based multi-source NMT methods . |
| Outcome: | The proposed approach achieves clear gains in translation quality and captures implicit invariance between different sources. |
Diverse Pretrained Context Encodings Improve Document Translation (2021.acl-long)
Copied to clipboard
| Challenge: | Existing models for sentence-level sequence-to-sequence translations do not use extra-sentential information. |
| Approach: | They propose a sentence-level sequence-to-sequence transformer with multiple pre-trained context signals. |
| Outcome: | The proposed model outperforms existing models on Chinese-English and English-German tasks. |
Weakly supervised discourse segmentation for multiparty oral conversations (2021.emnlp-main)
Copied to clipboard
| Challenge: | Discourse segmentation is the first step of discourse analysis. |
| Approach: | They propose a weak supervision approach to adapt a latent model to French conversation transcripts with a linguistic and acoustic input. |
| Outcome: | The proposed model improves in situations where speaker turns are lacking or noisy, gaining up to 13% in F-score. |
Bias Mitigation in Machine Translation Quality Estimation (2022.acl-long)
Copied to clipboard
| Challenge: | despite advances in machine translation, the accuracy and fluency of translations cannot be guaranteed without a reference translation. |
| Approach: | They propose to use auxiliary tasks to mitigate partial input bias . they aim to train a multitask architecture with an auxiliary binary classification task . |
| Outcome: | The proposed models reduce partial input bias while maintaining the overall performance. |
MORPHOGEN: A Multilingual Benchmark for Evaluating Gender-Aware Morphological Generation (2026.acl-long)
Copied to clipboard
| Challenge: | In morphologically rich languages, gender influences verb conjugation, pronouns, and even first-person constructions with explicit and implicit mentions of gender. |
| Approach: | They propose a morphologically grounded large-scale benchmark dataset for evaluating gender-aware generation in three typologically diverse grammatically gendered languages: French, Arabic, and Hindi. |
| Outcome: | The proposed dataset compares 15 popular multilingual large language models on their ability to handle morphological gender and morphology agreement. |
Disentangling the Roles of Target-side Transfer and Regularization in Multilingual Machine Translation (2024.eacl-long)
Copied to clipboard
| Challenge: | Multilingual Machine Translation (MMT) benefits from knowledge transfer across different language pairs, but performance differences between one-to-many and many-to-1 translation are negligible. |
| Approach: | They conduct a large-scale study that varies the auxiliary target-side languages along two dimensions to show the dynamic impact of knowledge transfer on the main language pairs. |
| Outcome: | The proposed model can translate between multiple languages with minimal positive transfer ability. |
Refining Source Representations with Relation Networks for Neural Machine Translation (C18-1)
Copied to clipboard
| Challenge: | Existing neural machine translation frameworks that forget distant information and disregard relationship between source and target words are not effective. |
| Approach: | They propose to use relation networks to learn better representations of the source . they propose to associate source words with each other to help retain their relationships . |
| Outcome: | Experiments show that the proposed approach outperforms the encoder-decoder framework on several datasets. |
A Testset for Context-Aware LLM Translation in Korean-to-English Discourse Level Translation (2025.coling-main)
Copied to clipboard
| Challenge: | Recent studies indicate that for high-resource languages, LLM surpasses encoder-decoder neural machine translation (NMT) models. |
| Approach: | They propose to construct a Korean-English discourse-level corpus with 600 text instances featuring six linguistic phenomena: lexical ambiguity, zero anaphora, slang, idiom, figurative language, and implicature. |
| Outcome: | The proposed corpus of 600 text instances features six linguistic phenomena, including lexical ambiguity, zero anaphora, slang, idiom, figurative language, and implicature. |
A Survey of Domain Adaptation for Neural Machine Translation (C18-1)
Copied to clipboard
| Challenge: | Neural machine translation (NMT) is a deep learning based approach for machine translation. |
| Approach: | They propose to use a deep learning approach to train machine translation in scenarios where large-scale parallel corpora are available. |
| Outcome: | The proposed approach yields the state-of-the-art translation performance in resource rich scenarios. |
Towards Example-Based NMT with Multi-Levenshtein Transformers (2023.emnlp-main)
Copied to clipboard
| Challenge: | Retrieval-augmented machine translation (RAMT) is attracting growing attention . it is assumed to implement some form of domain adaptation . |
| Approach: | They propose a retrieval-augmented version of the Levenshtein Transformer to make it more transparent . they propose to perform training and inference in this model, based on multi-way alignment algorithms and imitation learning. |
| Outcome: | The proposed architecture improves translation performance and improves consistency of translations compared to previous models. |
Word Embedding and WordNet Based Metaphor Identification and Interpretation (P18-1)
Copied to clipboard
| Challenge: | Existing models cannot identify exact metaphorical words within a sentence . current models do not rely on hand-crafted knowledge for training . |
| Approach: | They propose an unsupervised learning method that identifies and interprets metaphors at word-level without preprocessing. |
| Outcome: | The proposed method outperforms baseline models in two translation systems for English to Chinese showing that it paraphrases metaphors into their literal counterparts. |
Multilingual Neural Machine Translation: Can Linguistic Hierarchies Help? (2021.findings-emnlp)
Copied to clipboard
| Challenge: | Multilingual Neural Machine Translation (MNMT) trains a single model that supports translation between multiple languages . transferring knowledge from a diverse set of languages degrades the translation performance due to negative transfer. |
| Approach: | They propose a hierarchical knowledge distillation approach to train multilingual models . they use typological features and phylogeny to overcome negative transfer issue . |
| Outcome: | The proposed approach avoids negative transfer effect by capitalising on language groups generated according to typological features and phylogeny of languages. |
A Stochastic Decoder for Neural Machine Translation (P18-1)
Copied to clipboard
| Challenge: | Neural machine translation models do not account for local lexical and syntactic variation in parallel corpora. |
| Approach: | They propose a deep generative model of machine translation which incorporates a chain of latent variables to account for local lexical and syntactic variation in parallel corpora. |
| Outcome: | The proposed model consistently improves over strong baselines on several different language pairs. |
Context-Aware Neural Machine Translation Learns Anaphora Resolution (P18-1)
Copied to clipboard
| Challenge: | Standard machine translation systems process sentences in isolation and ignore extra-sentential information. |
| Approach: | They propose a context-aware neural machine translation model that controls flow of information from extended context to the translation model. |
| Outcome: | The proposed model improves on an English-Russian subtitles dataset over its context-agnostic version (+0.7) and over simple concatenation of context and source sentences (+0.6). |
CHENGYU-BENCH: Benchmarking Large Language Models for Chinese Idiom Understanding and Use (2025.emnlp-main)
Copied to clipboard
| Challenge: | Existing benchmarks focus on narrow tasks such as multiple-choice cloze tests, isolated translation, or simple paraphrasing. |
| Approach: | They propose a benchmark to measure Chinese idioms' cultural and contextual nuances . they evaluate 2,937 human-verified examples covering 1,765 common idiomes . |
| Outcome: | The proposed benchmarks achieve 95% accuracy on Evaluative Connotation, but only 85% on Appropriateness and 40% top-1 accuracy in Open Cloze. |
Extracting Parallel Sentences with Bidirectional Recurrent Neural Networks to Improve Machine Translation (C18-1)
Copied to clipboard
| Challenge: | Parallel sentence extraction is a task addressing the data sparsity problem found in multilingual natural language processing applications. |
| Approach: | They propose a bidirectional recurrent neural network based approach to extract parallel sentences from multilingual corpora. |
| Outcome: | The proposed approach outperforms existing approaches on noisy parallel corpora and shows significant improvements in translation performance. |
Modeling Recurrence for Transformer (N19-1)
Copied to clipboard
| Challenge: | Existing studies show that the lack of recurrence modeling hinders the development of a translation model. |
| Approach: | They propose to model recurrence for Transformer with an additional recurrent encoder. |
| Outcome: | The proposed model outperforms the deep model on EnglishGerman and ChineseEnglish translation tasks. |
AfriVox: Probing Multilingual and Accent Robustness of Speech LLMs (2026.eacl-long)
Copied to clipboard
Busayo Awobade, Mardhiyah Sanni, Tassallah Abdullahi, Chibuzor Okocha, Kelechi Ezema, Devendra Deepak Kayande, Lukman Enegi Ismaila, Tobi Olatunji, Gloria Ashiya Katuka
| Challenge: | Recent advances in multimodal and speech-native large language models have delivered impressive speech recognition, translation, understanding, and question-answering capabilities for high-resource languages. |
| Approach: | They propose to benchmark African languages and African-accented French, Arabic, and 100+ African English accents across 20 African languages. |
| Outcome: | The proposed model outperforms traditional speech transcription and translation models in African languages and non-native French or English accents. |
A Benchmark for Translations Across Styles and Language Variants (2025.findings-emnlp)
Copied to clipboard
| Challenge: | lack of comprehensive evaluation benchmarks has hindered progress in this field . lack of evaluation benchmarking has hinder MT's ability to generate accurate outputs . |
| Approach: | They evaluate translations across semantic preservation, cultural and regional specificity, expression style, and fluency at both the word and sentence levels. |
| Outcome: | The proposed evaluation framework is validated on translations of state-of-the-art large language models . |
HISTOIRESMORALES: A French Dataset for Assessing Moral Alignment (2025.naacl-long)
Copied to clipboard
Thibaud Leteno, Irina Proskurina, Antoine Gourru, Julien Velcin, Charlotte Laclau, Guillaume Metzler, Christophe Gravier
| Challenge: | HistoiresMorales is a dataset based on moralStories in French . it is based upon annotations of moral values within the dataset . |
| Approach: | They propose a dataset in French that aims to align language models with moral values . they use annotations to ensure their alignment with French norms . |
| Outcome: | The proposed dataset guarantees grammatical accuracy and adaptation to the French cultural context. |
Multilingual word translation using auxiliary languages (D19-1)
Copied to clipboard
| Challenge: | Existing multilingual word translation methods focus on learning mappings from each language to a shared space. |
| Approach: | They propose a multilingual translation procedure that uses all the learned mappings to translate a word from one language to another. |
| Outcome: | Experiments on a standard multilingual word translation benchmark show that the proposed translation procedure outperforms state-of-the-art translation methods. |
AnyTrans: Translate AnyText in the Image with Large Scale Models (2024.findings-emnlp)
Copied to clipboard
| Challenge: | Recent advances in natural language processing and computer vision have made it possible to translate images with text in one language into equivalent images displaying that text translated into another language. |
| Approach: | They propose an all-encompassing framework for the task–In-Image Machine Translation (IIMT) that incorporates contextual cues from both textual and visual elements during translation. |
| Outcome: | The proposed framework can be constructed using open-source models and requires no training, making it highly accessible and expandable. |
BiTIIMT: A Bilingual Text-infilling Method for Interactive Machine Translation (2022.acl-long)
Copied to clipboard
| Challenge: | Existing IMT systems relying on lexical constrained decoding (LCD) are limited in translation efficiency and quality due to LCD. |
| Approach: | They propose a novel interactive neural machine translation system that uses lexical constraints to decode missing words in a manually revised translation. |
| Outcome: | The proposed system performs significantly better and faster than state-of-the-art IMT on three translation tasks. |
Recurrent Positional Embedding for Neural Machine Translation (D19-1)
Copied to clipboard
| Challenge: | Existing translation systems that use positional embeddings only encode static order dependencies based on discrete numerical information, which may hinder the improvement of translation capacity. |
| Approach: | They propose a recurrent positional embedding approach based on word vectors that are learned by a neural network and integrated into existing multi-head self-attention models. |
| Outcome: | The proposed approach improves translation performance over the state-of-the-art Transformer baseline in English-to-German and NIST Chinese-to English translation tasks. |
C-XNLI: Croatian Extension of XNLI Dataset (2023.findings-acl)
Copied to clipboard
| Challenge: | Existing parallel datasets limit multilingual evaluations due to the nature of linguistic annotation, which is tedious, subjective, and costly. |
| Approach: | They extend the Cross-lingual Natural Language Inference corpus with Croatian and use Facebook's 1.2B parameter m2m_100 model to analyze the train set and compare its quality with the existing machine-translated German set. |
| Outcome: | The proposed model is consistent with other XNLI dubs and is compared with the existing machine-translated German train set. |
Exploiting Pre-Ordering for Neural Machine Translation (L18-1)
Copied to clipboard
| Challenge: | Existing studies have shown that Neural Machine Translation suffers from the problems that some source words are mistakenly translated for multiple times . |
| Approach: | They propose a pre-ordering approach to solve the under-translation problem by pre-ordnanced source sentences and position embedding to enhance monotone translation. |
| Outcome: | The proposed method significantly improves translation quality by 2.43 BLEU points on Chinese-to-English translation. |
One Sentence One Model for Neural Machine Translation (L18-1)
Copied to clipboard
| Challenge: | Neural machine translation (NMT) is a new state of the art that can produce better results than traditional statistical machine translation. |
| Approach: | They propose a dynamic neural network which learns a general network as usual and fine-tunes it for each test sentence. |
| Outcome: | The proposed method improves translation performance when similar sentences are available. |
A Variational Hierarchical Model for Neural Cross-Lingual Summarization (2022.acl-long)
Copied to clipboard
| Challenge: | Existing studies on cross-lingual summarization focus on pipeline methods or jointly training an end-to-end model through an auxiliary MT or MS objective. |
| Approach: | They propose a hierarchical model for the cross-lingual summarization task . the model is based on the conditional variational auto-encoder . |
| Outcome: | The proposed model generates better cross-lingual summaries than comparison models in the few-shot setting. |
Examining the Tip of the Iceberg: A Data Set for Idiom Translation (L18-1)
Copied to clipboard
| Challenge: | Neural Machine Translation (NMT) has been widely used in recent years with significant improvements for many language pairs. |
| Approach: | They propose to use a large-scale data set to evaluate idiom translation in GermanEnglish. |
| Outcome: | The proposed dataset is used to perform preliminary NMT experiments on idiom translation in GermanEnglish. |
Encoders Help You Disambiguate Word Senses in Neural Machine Translation (D19-1)
Copied to clipboard
| Challenge: | Neural machine translation models can perform word sense disambiguation (WSD) however, it is unclear which component dominates the process of disambiguating words. |
| Approach: | They evaluate hidden states and investigate distributions of self-attention in NMT encoders and decoders to disambiguate word senses. |
| Outcome: | The proposed model outperforms encoder hidden states on large datasets . the model outpersforms decoders on large data sets . |
Source and Target Bidirectional Knowledge Distillation for End-to-end Speech Translation (2021.naacl-main)
Copied to clipboard
| Challenge: | End-to-end speech translation models can be trained to leverage source text . however, since the input modalities are different, it is difficult to leverage the source text successfully. |
| Approach: | They propose to leverage source transcriptions via pre-training and joint training with ASR and NMT tasks. |
| Outcome: | The proposed model predicts paraphrased transcriptions as an auxiliary task with a single decoder. |
“You Sound Just Like Your Father” Commercial Machine Translation Systems Include Stylistic Biases (2020.acl-main)
Copied to clipboard
| Challenge: | a recent study shows that machine translations make older and more male characters sound older and older than the original. |
| Approach: | They propose to use demographicallyrepresentative data to examine how text is translated . they show that authors sound older and more male than the original . |
| Outcome: | The results suggest that translation models reflect demographic bias in the training data. |
Curated Datasets and Neural Models for Machine Translation of Informal Registers between Mayan and Spanish Vernaculars (2024.naacl-long)
Copied to clipboard
| Challenge: | a set of corpora in several Mayan languages spoken in Guatemala and Mexico is published . the languages are considered to be somewhat in decline in terms of resources and global exposure . |
| Approach: | They develop, curate, and publicly release a set of corpora in several Mayan languages spoken in Guatemala and southern Mexico, which they call MayanV. |
| Outcome: | The proposed datasets are parallel with Spanish, the dominant language of the region, and differ in register from most other available resources. |
Alignment verification to improve NMT translation towards highly inflectional languages with limited resources (2021.eacl-main)
Copied to clipboard
| Challenge: | Existing approaches to improve translation quality using limited training data are phrase-based and syntax-based approaches. |
| Approach: | They propose to combine a neural MT system with an open source module to improve translation quality. |
| Outcome: | The proposed method improves translation quality over the best individual NMT and the standard ensemble system provided in the Marian-NMT system. |
Few-Shot Learning Translation from New Languages (2025.emnlp-main)
Copied to clipboard
| Challenge: | Recent work shows strong transfer learning capability to unseen languages in sequence-to-sequence neural networks . current transfer learning methods require much less downstream task data than would otherwise be required. |
| Approach: | They first train word embeddings models on varying amounts of data and plug them into a machine translation model. |
| Outcome: | The proposed model can learn Flores with only 500 parallel sentences and 31,250 sentences of monolingual data, and it can exceed 15 BLEU on unseen languages. |
NeighXLM: Enhancing Cross-Lingual Transfer in Low-Resource Languages via Neighbor-Augmented Contrastive Pretraining (2025.findings-emnlp)
Copied to clipboard
| Challenge: | NeighXLM is a neighbor-augmented contrastive pretraining framework . it exploits intra-language semantic relationships captured during pretraining to construct high-quality positive pairs. |
| Approach: | They propose a neighbor-augmented contrastive pretraining framework that mines semantic neighbors from unlabeled corpora to enrich target-language supervision. |
| Outcome: | The proposed framework enriches target-language supervision by mining semantic neighbors from unlabeled corpora. |
Controlling Styles in Neural Machine Translation with Activation Prompt (2023.findings-acl)
Copied to clipboard
| Challenge: | Earlier studies on controlling styles in neural machine translation (NMT) have focused on regulating the level of formality, but they still encounter two major challenges. |
| Approach: | They propose a method to control the style of neural machine translation by retrieving prompts from stylized monolingual corpus. |
| Outcome: | The proposed method can control the style of translation and achieve remarkable performance. |
Accelerating Neural Transformer via an Average Attention Network (P18-1)
Copied to clipboard
| Challenge: | Using parallelizable attention networks, the neural Transformer is slow to train due to auto-regressive architecture and self-attention in the decoder. |
| Approach: | They propose an average attention network to replace the original self-attention model in the decoder of the neural Transformer. |
| Outcome: | The proposed network can decode sentences over four times faster than the original version with almost no loss in training time and translation performance. |
Efficient CTC Regularization via Coarse Labels for End-to-End Speech Translation (2023.eacl-main)
Copied to clipboard
| Challenge: | Developing techniques to support end-to-end speech translation is non-trivial because of the speech-text modality gap. |
| Approach: | They propose a coarse labeling approach that merges vocabulary labels via simple heuristic rules . they propose to use 256-bit truncation, division or modulo operations to regularize the encoder . |
| Outcome: | The proposed method can increase training efficiency while delivering better performance. |
Beyond Triplet: Leveraging the Most Data for Multimodal Machine Translation (2023.findings-acl)
Copied to clipboard
| Challenge: | Multimodal machine translation (MMT) aims to improve translation quality by incorporating information from other modalities, such as vision. |
| Approach: | They propose a framework for multimodal machine translation that utilizes large-scale non-triple data and a multimodal translation dataset. |
| Outcome: | The proposed method can significantly improve translation performance with more non-triple data. |
Hierarchical Modeling of Global Context for Document-Level Neural Machine Translation (D19-1)
Copied to clipboard
| Challenge: | Document-level machine translation (MT) remains challenging due to the difficulty in efficiently using document context. |
| Approach: | They propose a hierarchical model to learn document context for document-level neural machine translation . they use a sentence encoder to capture intra-sentence dependencies and a document encoder . |
| Outcome: | The proposed model significantly improves document-level translation performance over strong baselines. |
Syntax-guided Localized Self-attention by Constituency Syntactic Distance (2022.findings-emnlp)
Copied to clipboard
Shengyuan Hou, Jushi Kai, Haotian Xue, Bingyu Zhu, Bo Yuan, Longtao Huang, Xinbing Wang, Zhouhan Lin
| Challenge: | Recent studies have shown that Transformers is implicitly learning syntactic information from data, albeit is highly dependent on the quality and scale of the training data. |
| Approach: | They propose a syntax-guided localized self-attention model that allows directly incorporating grammar structures from an external constituency parser. |
| Outcome: | The proposed model improves translation performance on a variety of datasets, from small to large datasets and with different source languages. |
Bridging the Gap between Synthetic and Authentic Images for Multimodal Machine Translation (2023.emnlp-main)
Copied to clipboard
| Challenge: | Existing models require associated image with input sentence, which is difficult to satisfy at inference. |
| Approach: | They propose to use synthetic and authentic images to generate translations using text-to-image generation models. |
| Outcome: | The proposed model achieves state-of-the-art performance on En-De and En-Fr datasets while remaining independent of authentic images during inference. |
Does Summary Evaluation Survive Translation to Other Languages? (2022.naacl-main)
Copied to clipboard
| Challenge: | a quality summarization dataset requires the production and evaluation of summaries by trained humans and machines. |
| Approach: | They translate a summarization dataset in English and compare its performance to seven languages . they explore equivalence testing as an appropriate statistical paradigm for evaluating correlations between human and automated scoring of summaries . |
| Outcome: | The proposed method could be used in seven languages and compares performance across measures. |
Subword Segmental Machine Translation: Unifying Segmentation and Target Sentence Generation (2023.findings-acl)
Copied to clipboard
| Challenge: | Subword segmenters are used in neural machine translation, but are not used in high-resource settings. |
| Approach: | They propose a subword segmental machine translation (SSMT) that unifies subword and MT in a single trainable model. |
| Outcome: | The proposed model improves chrF scores for morphologically rich agglutinative languages and is more robust on a test set constructed for evaluating morphology generalisations. |
Modeling Dual Read/Write Paths for Simultaneous Machine Translation (2022.acl-long)
Copied to clipboard
| Challenge: | Simultaneous machine translation (SiMT) outputs translation while reading source sentence . existing methods do not direct the read/write path, resulting in poor performance . |
| Approach: | They propose a method which introduces duality constraints to direct the read/write path . they propose to map the read path in two SiMT models to satisfy duality constraint . |
| Outcome: | Experiments on En-Vi and De-En tasks show that the proposed method outperforms baselines under all latency. |
Data Rejuvenation: Exploiting Inactive Training Examples for Neural Machine Translation (2020.emnlp-main)
Copied to clipboard
| Challenge: | Large-scale training datasets make training neural machine translation models difficult. |
| Approach: | They propose to identify inactive training examples which contribute less to the model performance and introduce data rejuvenation to improve NMT models' training. |
| Outcome: | The proposed framework stabilizes and accelerates the training process of NMT models, resulting in models with better generalization capability. |
Generating Diverse Translations with Sentence Codes (P19-1)
Copied to clipboard
| Challenge: | Existing methods to generate diverse translations use different sentence structures . Xu et al., 2018: generating multiple valid translations with high diversity is difficult . |
| Approach: | They propose to use sentence codes to condition the sentence generation to obtain diverse translations . they propose to sample multiple candidates, each of which conditioned on a unique code . |
| Outcome: | The proposed method generates paraphrase translations with drastically different structures . the proposed method can be easily adopted to existing translation systems . |
Learning Adaptive Segmentation Policy for Simultaneous Translation (2020.emnlp-main)
Copied to clipboard
| Challenge: | Experimental results show that adaptive segmentation policies for simultaneous translation are more accurate than current methods . if translation starts before adequate source content is delivered, the quality of translation degrades . waiting for too much source text increases latency, which would hurt accuracy . |
| Approach: | They propose a new adaptive segmentation policy for simultaneous translation based on human interpreters . it learns to segment the source text by considering possible translations produced by the translation model . |
| Outcome: | Experimental results show that the proposed method achieves better accuracy-latency trade-off over state-of-the-art methods. |
Exploring Phoneme-Level Speech Representations for End-to-End Speech Translation (P19-1)
Copied to clipboard
| Challenge: | Previous work on end-to-end translation from speech uses frame-level features as speech representations, which creates longer, sparser sequences than text. |
| Approach: | They propose a method to generate compressed phoneme-like speech representations that generate shorter, higher-level source sequences for translation. |
| Outcome: | The proposed method improves translation performance by 5 BLEU on high and low resource languages and reduces training time by 60%. |
Simultaneous Machine Translation with Visual Context (2020.emnlp-main)
Copied to clipboard
| Challenge: | Simultaneous machine translation (SiMT) aims to reproduce human interpretation, where an interpreter translates spoken utterances as they are produced. |
| Approach: | They propose to add visual context to siMT to compensate for the missing source context . they show visual-grounded models are much better than commonly used global features . |
| Outcome: | The proposed models reach up to 3 BLEU points improvement under low latency scenarios. |
Measuring and Mitigating Name Biases in Neural Machine Translation (2022.acl-long)
Copied to clipboard
| Challenge: | Neural machine translation systems exhibit problematic biases, such as stereotypical gender bias in occupation terms. |
| Approach: | They propose a method to reduce biases in person name translations by randomly switching entities during translation. |
| Outcome: | The proposed method eliminates the problem without any effect on translation quality. |
A Preference-driven Paradigm for Enhanced Translation with Large Language Models (2024.naacl-long)
Copied to clipboard
| Challenge: | Recent research shows that large language models (LLMs) can achieve remarkable translation performance through supervised fine-tuning (SFT) however, SFT simply instructs the model to imitate reference translations token by token, making it vulnerable to the noise present in the data. |
| Approach: | They propose a preference-based approach to supervised fine-tuning that trains the model to imitate reference translations token by token, making it vulnerable to noise. |
| Outcome: | The proposed approach overcomes the plateau associated with imitation-based SFT and is more resilient in the absence of gold translations. |
An Efficient Gloss-Free Sign Language Translation Using Spatial Configurations and Motion Dynamics with LLMs (2025.naacl-long)
Copied to clipboard
| Challenge: | Existing methods for sign language translation rely on glosses, which are written representations of signs. |
| Approach: | They propose a new LLM-based SLT framework that uses off-the-shelf visual encoders to extract spatial and motion features from sign videos. |
| Outcome: | The proposed framework captures spatial configurations and motion dynamics in sign language without domain-specific tuning. |
Beyond Sentence-Level End-to-End Speech Translation: Context Helps (2021.acl-long)
Copied to clipboard
| Challenge: | Document-level contextual information has shown benefits to text-based machine translation, but whether and how it helps end-to-end speech translation is still under-studied. |
| Approach: | They propose a concatenation-based ST model with adaptive feature selection for computational efficiency. |
| Outcome: | The proposed model improves translation quality and robustness to (artificial) audio segmentation errors. |
SBAAM! Eliminating Transcript Dependency in Automatic Subtitling (2024.acl-long)
Copied to clipboard
| Challenge: | Subtitling is a crucial task for enhancing the accessibility of audiovisual content and relying on automatic transcripts for the three subtasks is uncharted territory. |
| Approach: | They propose a model capable of producing automatic subtitles, completely eliminating any dependence on intermediate transcripts also for timestamp prediction. |
| Outcome: | Experimental results show that the proposed model eliminates the need for intermediate transcripts for timestamp prediction across multiple language pairs and diverse conditions. |
Stacked Acoustic-and-Textual Encoding: Integrating the Pre-trained Models into Speech Translation Encoders (2021.acl-long)
Copied to clipboard
| Challenge: | End-to-end Speech Translation (E2E ST) encoders lack global context representation, whereas MT encoder lacks it. |
| Approach: | They propose a Stacked Acoustic-and-Textual Encoding method for speech translation . they propose an adaptor module to alleviate representation inconsistency . |
| Outcome: | The proposed method achieves state-of-the-art BLEU scores of 18.3 and 25.2 on two ST tasks. |
Improving Neural Machine Translation with Neural Syntactic Distance (N19-1)
Copied to clipboard
| Challenge: | Neural syntactic distance (NSD) is used to represent constituent trees using a sequence whose length is identical to the number of words in the sentence. |
| Approach: | They propose five strategies to improve NMT with explicit use of syntactic information . et al., 2014) propose a set of five strategies that incorporate syntastic information into the encoder and/or decoder of the baseline model. |
| Outcome: | The proposed strategies improve translation performance of the baseline model (+2.1 (En–Ja), +1.3 (Ja–En), +1.2 (En-Ch), and +1.0 (Ch–En) BLEU. |
Explore More Guidance: A Task-aware Instruction Network for Sign Language Translation Enhanced with Data Augmentation (2022.findings-naacl)
Copied to clipboard
| Challenge: | Existing studies focus on the recognition step, while paying less attention to sign language translation. |
| Approach: | They propose a task-aware instruction network, namely TIN-SLT, for sign language translation, by introducing the isntruction module and the learning-based feature fuse strategy into a Transformer network. |
| Outcome: | The proposed system outperforms existing solutions on two benchmark datasets, PHOENIX-2014-T and ASLG-PC12, and outperformed previous best solutions by 1.65 and 1.42 in terms of BLEU-4. |
Can ChatGPT Really Understand Modern Chinese Poetry? (2026.findings-eacl)
Copied to clipboard
| Challenge: | Recent studies have focused on poetry generation and translation, but their scope has been limited to evaluation and analysis of experimental results without addressing fundamental issues of comprehension. |
| Approach: | They propose a framework for evaluating ChatGPT's understanding of modern poetry . they evaluated the interpretations of unpublished modern Chinese poems by different poets . |
| Outcome: | The proposed framework is based on the evaluation of unpublished poems by poets and shows that its interpretations align with the original poets’ intents in over 73% of the cases. |
TEaR: Improving LLM-based Machine Translation with Systematic Self-Refinement (2025.findings-naacl)
Copied to clipboard
Zhaopeng Feng, Yan Zhang, Hao Li, Bei Wu, Jiayu Liao, Wenqiang Liu, Jun Lang, Yang Feng, Jian Wu, Zuozhu Liu
| Challenge: | Large Language Models (LLMs) have achieved impressive results in Machine Translation (MT). human evaluations reveal that LLM-generated translations still contain various errors. |
| Approach: | They propose a LLM-based self-refinement framework that feeds error information back into LLMs to facilitate self-finement, leading to enhanced translation quality. |
| Outcome: | The proposed framework outperforms internal refinement and feedback methods while ensuring a robust translation quality baseline. |
Breaking the Corpus Bottleneck for Context-Aware Neural Machine Translation with Cross-Task Pre-training (2021.acl-long)
Copied to clipboard
| Challenge: | Context-aware neural machine translation (NMT) remains challenging due to the lack of large-scale document-level parallel corpora. |
| Approach: | They propose to use large-scale parallel datasets and source-side monolingual documents to improve context-aware neural machine translation. |
| Outcome: | The proposed model can be used to translate both sentences and documents on four translation tasks. |
LaCoMSA: Language-Consistency Multilingual Self-Alignment with Latent Representation Rewarding (2026.eacl-long)
Copied to clipboard
| Challenge: | Existing multilingual alignment methods mitigate these issues but rely on external supervision, such as translation systems or English-biased signal. |
| Approach: | They propose a preference optimization framework that leverages an LLM’s own latent representations as intrinsic supervision signals and rewards lower-resource language outputs based on their alignment with high-resourced (English) counterparts in the "semantic hub". |
| Outcome: | The proposed framework improves a Llama 3 8B model multilingual win rates by up to 6.8% absolute (55.0% relative) on X-AlpacaEval and achieves consistent gains across benchmarks and models. |
Mitigating Paraphrase Attacks on Machine-Text Detection via Paraphrase Inversion (2025.findings-acl)
Copied to clipboard
| Challenge: | Paraphrases applied to machine-generated texts can degrade performance of machine-text detectors. |
| Approach: | They propose an approach which frames the problem as translation from paraphrased text back to the original text. |
| Outcome: | The proposed approach yields an average improvement of +22% AUROC across seven detectors and three different domains. |
Robustness of Multi-Source MT to Transcription Errors (2023.findings-acl)
Copied to clipboard
| Challenge: | In multilingual settings, the same content may be available in various languages via simultaneous interpreting, dubbing or subtitling. |
| Approach: | They hypothesize that leveraging multiple sources will improve translation quality if the sources complement one another in terms of correct information they contain. |
| Outcome: | The proposed method is robust to speech recognition errors on a 10-hour ESIC corpus. |
Language Model-Driven Data Pruning Enables Efficient Active Learning (2026.findings-eacl)
Copied to clipboard
| Challenge: | Existing data pruning methods for active learning are expensive and time-consuming. |
| Approach: | They propose a plug-and-play data pruning strategy that leverages language models to prune the unlabeled pool. |
| Outcome: | The proposed pruning strategy outperforms existing pruning methods on translation, sentiment analysis, topic classification, and summarization tasks on diverse datasets. |
Neural Machine Translation with Contrastive Translation Memories (2022.emnlp-main)
Copied to clipboard
| Challenge: | Experimental results show that retrieval-augmented NMT model obtains substantial improvements over strong baselines in the benchmark dataset. |
| Approach: | They propose a retrieval-augmented NMT model that is holistically similar to the source sentence while individually contrastive to each other. |
| Outcome: | The proposed model improves on baselines in the translation task. |
MiTTenS: A Dataset for Evaluating Gender Mistranslation (2024.emnlp-main)
Copied to clipboard
| Challenge: | Existing studies on gender mistranslation in translation systems have highlighted the problem . a dataset of 26 languages is presented to measure the extent of such errors . |
| Approach: | They propose a dataset that measures the extent of gender mistranslation in translation systems . they use handcrafted passages that target known failure patterns and synthetically generated passages . |
| Outcome: | The proposed dataset covers 26 languages from a variety of language families and scripts, including several traditionally under-represented in digital resources. |
Effective Self-Mining of In-Context Examples for Unsupervised Machine Translation with LLMs (2025.findings-naacl)
Copied to clipboard
| Challenge: | Large Language Models (LLMs) have demonstrated impressive performance on a wide range of natural language processing tasks. |
| Approach: | They propose an unsupervised approach to mine in-context examples for machine translation (MT) they use word-level mining to acquire word translations that are then used to perform sentence-level mines . |
| Outcome: | The proposed approach outperforms state-of-the-art methods on 288 directions on 287 languages and is based on word-level mining and sentence-level extraction. |
Gaussian Multi-head Attention for Simultaneous Machine Translation (2022.findings-acl)
Copied to clipboard
| Challenge: | Existing methods for siMT do not explicitly model the alignment to perform the control. |
| Approach: | They propose to model alignment and translation in a unified manner by Gaussian Multi-head Attention (GMA) they propose to integrate alignment-related priors into the translation model to determine final attention. |
| Outcome: | The proposed method outperforms strong baselines on trade-off between translation and latency. |
Learning Translations via Images with a Massively Multilingual Image Dataset (P18-1)
Copied to clipboard
| Challenge: | Existing datasets for learning translations of words are limited to a few high-resource languages and unrealistically easy settings. |
| Approach: | They propose a large-scale multilingual corpus of images labeled with the word they represent to facilitate translation research. |
| Outcome: | The proposed method improves on an unsupervised technique that has been limited to a few languages and unrealistic settings. |
P-MMEval: A Parallel Multilingual Multitask Benchmark for Consistent Evaluation of LLMs (2025.emnlp-main)
Copied to clipboard
Yidan Zhang, Yu Wan, Boyi Deng, Baosong Yang, Hao-Ran Wei, Fei Huang, Bowen Yu, Dayiheng Liu, Junyang Lin, Fei Huang, Jingren Zhou
| Challenge: | Recent advances in large language models showcase varied multilingual capabilities across tasks . previous assessments focused on fundamental natural language processing (NLP) or isolated capability-specific tasks. |
| Approach: | They propose a multilingual multitask benchmark to assess multilingual capabilities . they use a large-scale benchmark covering fundamental and capability-specialized datasets . |
| Outcome: | The proposed benchmark compares models and tasks across languages and tasks and examines knowledge transfer from English to other languages. |
Improving Word Embedding Factorization for Compression Using Distilled Nonlinear Neural Decomposition (2020.findings-emnlp)
Copied to clipboard
| Challenge: | Word-embeddings are vital components of natural language processing (NLP) but they consume a lot of memory which poses a challenge for edge deployment. |
| Approach: | They propose an embedding compression method based on matrix decomposition and knowledge distillation that initializes weights of pre-trained word-embeddings and fine-tunes end-to-end. |
| Outcome: | The proposed method has higher BLEU score on translation and lower perplexity on language modeling compared to complex, difficult to tune methods. |
AI-Assisted Human Evaluation of Machine Translation (2025.naacl-long)
Copied to clipboard
| Challenge: | Annotation metrics are misaligned with the ideal measure of text quality and human evaluation remains the most accurate, reliable, and ultimate standard. |
| Approach: | They propose an annotation protocol that helps annotators mark erroneous parts of the translation and assign a final score. |
| Outcome: | The proposed protocol reduces the time per span annotation by half . the method reduces annotation budget by 25% with filtering of examples that the AI deems to be likely to be correct. |
A Self-Distillation Recipe for Neural Machine Translation (2025.findings-acl)
Copied to clipboard
| Challenge: | Existing methods for Neural Machine Translation (NMT) have been proven effective in improving the performance of computer vision tasks without pre-training a teacher. |
| Approach: | They propose a rank-order augmented Pearson correlation loss and an iterative distillation method to prevent the discrepancy of predictions between the student and a stronger teacher from disturbing the training. |
| Outcome: | The proposed method can lead to significant improvements over the strong Transformer baseline on low/middle/high-resource tasks, obtaining comparable or better performance with fewer layers. |
Encouraging Lexical Translation Consistency for Document-Level Neural Machine Translation (2021.emnlp-main)
Copied to clipboard
| Challenge: | Experimental results show document-level neural machine translation improves lexical consistency . inconsistent translations tend to confuse readers in some cases . |
| Approach: | They propose to use a word link to obtain a document word link and an auxiliary loss function to constrain that their translation should be consistent. |
| Outcome: | The proposed approach improves translation consistency on ChineseEnglish and EnglishFrench translation tasks. |
Learning to Rewrite for Non-Autoregressive Neural Machine Translation (2021.emnlp-main)
Copied to clipboard
| Challenge: | Existing non-autoregressive neural machine translations have poor inference speed but weak recognition of erroneous translation pieces. |
| Approach: | They propose an architecture to explicitly learn to rewrite the erroneous translation pieces. |
| Outcome: | The proposed architecture can achieve better performance while significantly reducing decoding time. |
Prevent the Language Model from being Overconfident in Neural Machine Translation (2021.acl-long)
Copied to clipboard
| Challenge: | Neural Machine Translation models are based on partial translation and a language model that predicts the next token based only on partial. |
| Approach: | They propose a Margin-based Token-level Objective and a Sentence-level Goal to maximize the Margin . they propose to model the next token based on partial translation . |
| Outcome: | The proposed approach improves translation adequacy and fluency on English-to-German, Chinese-to English and French translation tasks. |
Ethical Considerations for Machine Translation of Indigenous Languages: Giving a Voice to the Speakers (2023.acl-long)
Copied to clipboard
| Challenge: | In recent years, machine translation has become very successful for high-resource language pairs. |
| Approach: | They conduct interviews with community leaders, teachers, and language activists to shed light on ethical considerations for the automatic translation of Indigenous languages. |
| Outcome: | The results show that the inclusion of native speakers and community members is vital to performing better and more ethical research on Indigenous languages. |
Contextual Metric Meta-Evaluation by Measuring Local Metric Accuracy (2025.findings-naacl)
Copied to clipboard
| Challenge: | Existing approaches to metric meta-evaluation focus on general statements about absolute and relative quality of metrics across arbitrary system outputs, but in practice, metrics are applied in highly contextual settings. |
| Approach: | They propose a method for contextual metric meta-evaluation by comparing local metric accuracy. |
| Outcome: | The proposed method compares the local metric accuracy of evaluation metrics across translation, speech recognition, and ranking tasks. |
Deconvolution-Based Global Decoding for Neural Machine Translation (C18-1)
Copied to clipboard
| Challenge: | Existing models for Neural Machine Translation (NMT) use Recurrent Neural Network (RNN) to generate translation word by word following a sequential order. |
| Approach: | They propose a Neural Machine Translation (NMT) model that decodes the sequence with the guidance of its structural prediction of the target-side context. |
| Outcome: | The proposed model is more competitive compared with the state-of-the-art methods and reduces repetition with the instruction from the target-side context for decoding. |
A Challenge Set and Methods for Noun-Verb Ambiguity (D18-1)
Copied to clipboard
| Challenge: | English part-of-speech taggers make egregious errors related to noun-verb ambiguity, despite having achieved 97%+ accuracy on the WSJ Penn Treebank since 2002. |
| Approach: | They propose to use a WSJ dataset to identify 30,000 examples of noun-verb ambiguity . they find that english part-of-speech taggers make egregious errors related to nouns and verbs . |
| Outcome: | The proposed model improves on the WSJ Penn Treebank by 14% and 52% relative to the previous model. |
AraDiCE: Benchmarks for Dialectal and Cultural Capabilities in LLMs (2025.coling-main)
Copied to clipboard
Basel Mousi, Nadir Durrani, Fatema Ahmad, Md. Arid Hasan, Maram Hasanain, Tameem Kabbani, Fahim Dalvi, Shammur Absar Chowdhury, Firoj Alam
| Challenge: | a recent study has found that Arabic is underrepresented in Large Language Models, especially in dialectal variations. |
| Approach: | They propose a benchmark for Arabic Dialect and Cultural Evaluation that evaluates Arabic dialect comprehension and generation. |
| Outcome: | The proposed model outperforms multilingual models on dialect comprehension and generation, but significant challenges persist in dialect identification, generation, and translation. |
Reference Network for Neural Machine Translation (P19-1)
Copied to clipboard
| Challenge: | Neural Machine Translation (NMT) generates translations in isolation, resulting in translation inconsistency and ambiguity. |
| Approach: | They propose to incorporate referring process into translation decoding of NMT by using local coordinates coding to obtain global context vectors containing monolingual and bilingual contextual information. |
| Outcome: | The proposed model improves translation quality with lightweight computation cost on Chinese-English and English-German translation tasks. |
Retrieving Sequential Information for Non-Autoregressive Neural Machine Translation (P19-1)
Copied to clipboard
| Challenge: | Experimental results show that the Reinforce-NAT system surpasses the baseline NAT system by a significant margin on BLEU without decelerating the decoding speed. |
| Approach: | They propose a sequence-level training method and a Transformer decoder to fuse the target sequential information into the top layer of the decoded Transformer. |
| Outcome: | The proposed model surpasses the baseline NAT system on BLEU without decelerating the decoding speed and achieves comparable translation performance to the autoregressive Transformer model with considerable speedup. |
Aligning Translation-Specific Understanding to General Understanding in Large Language Models (2024.emnlp-main)
Copied to clipboard
| Challenge: | Large Language models (LLMs) have remarkable abilities in understanding complex texts . however, understanding misalignment leads to LLMs mistakenly translating complex concepts . |
| Approach: | They propose a translation process that aligns the translation-specific understanding with the general understanding to improve translation quality and reduce translation literalness. |
| Outcome: | The proposed translation process improves translation quality and reduces translation literalness by -25% -51%. |
Towards Debiasing Translation Artifacts (2022.naacl-main)
Copied to clipboard
| Challenge: | Existing studies show translation artifacts in translations influence performance of cross-lingual tasks. |
| Approach: | They propose a method to reduce translation artifacts by extending an established bias-removal technique. |
| Outcome: | The proposed method reduces translationese at sentence and word level . it is the first study to debias translations on a natural language inference task . |
Translating Translationese: A Two-Step Approach to Unsupervised Machine Translation (P19-1)
Copied to clipboard
| Challenge: | Using a dictionary, given a rough, target language natives can uncover the latent, fully-fluent rendering of the translation. |
| Approach: | They propose a method that breaks translation into two steps by generating a dictionary and then ‘translating’ the resulting pseudo-translation into a fully fluent translation. |
| Outcome: | The proposed method 'gets better translation results on high-resource languages than previously published unsupervised MT studies' |
CLIcK: A Benchmark Dataset of Cultural and Linguistic Intelligence in Korean (2024.lrec-main)
Copied to clipboard
| Challenge: | Existing benchmark datasets for Korean cultural and linguistic knowledge are derived from the English counterparts through translation, so they overlook cultural contexts. |
| Approach: | They propose to use Korean cultural and linguistic intelligence to assess Korean model performance by providing fine-grained annotations of cultural and cultural knowledge. |
| Outcome: | The proposed dataset includes 1,995 QA pairs and is based on 1,992 Korean exams and textbooks. |
Lattice-Based Transformer Encoder for Neural Machine Translation (P19-1)
Copied to clipboard
| Challenge: | Neural machine translation (NMT) takes deterministic sequences for source representations. However, word-level or subword-level segmentation has multiple choices to split a source sequence with different word segmentors or different subword vocabulary sizes. |
| Approach: | They propose lattice-based encoders to explore effective word or subword representations in an automatic way during training. |
| Outcome: | The proposed encoders can explore effective word or subword representation in an automatic way during training. |
VoiceTextBlender: Augmenting Large Language Models with Speech Capabilities via Single-Stage Joint Speech-Text Supervised Fine-Tuning (2025.naacl-long)
Copied to clipboard
Yifan Peng, Krishna C Puvvada, Zhehuai Chen, Piotr Zelasko, He Huang, Kunal Dhawan, Ke Hu, Shinji Watanabe, Jagadeesh Balam, Boris Ginsburg
| Challenge: | Recent studies have augmented large language models (LLMs) with speech capabilities, leading to the development of speech language models. |
| Approach: | They propose a single-stage joint speech-text SFT approach for training SpeechLMs . their model combines text-only SFT data with three types of speech-related data . |
| Outcome: | The proposed model outperforms previous SpeechLMs on speech-based QA tasks while maintaining original speech-only capabilities. |
That was the last straw, we need more: Are Translation Systems Sensitive to Disambiguating Context? (2023.findings-emnlp)
Copied to clipboard
| Challenge: | Existing models for translation of ambiguous text use context to disambiguate meaning . current models for MTs consistently translate English idioms literally, whereas LMs are context-aware . |
| Approach: | They use a dataset of 512 pairs of English sentences to study semantic ambiguities . they use literal and figurative idioms to disambiguate intended meaning . |
| Outcome: | The results show that current models translate English idioms literally, even when the context suggests a figurative interpretation. |
Translation Deserves Better: Analyzing Translation Artifacts in Cross-lingual Visual Question Answering (2024.findings-acl)
Copied to clipboard
ChaeHun Park, Koanho Lee, Hyesu Lim, Jaeseok Kim, Junmo Park, Yu-Jung Heo, Du-Seong Chang, Jaegul Choo
| Challenge: | Recent studies have employed machine translation systems for cross-lingual VQA tasks . however, translated texts contain unique characteristics distinct from human-written ones, referred to as translation artifacts. |
| Approach: | They propose a machine translation system that can train models in multiple languages . they propose augmentation strategies that reduce translation artifacts in translated texts . |
| Outcome: | The proposed approach reduces translation artifacts in models across languages and languages. |
End-to-End Lexically Constrained Machine Translation for Morphologically Rich Languages (2021.acl-long)
Copied to clipboard
| Challenge: | Existing approaches to enforce word forms in translations struggle to make them agree with the rest of the output. |
| Approach: | They propose to train neural machine translation models with lemmatized constraints to infer correct word inflection. |
| Outcome: | The proposed model reduces errors in translation of constrained terms in automatic and manual evaluations on English-Czech language pairs. |
NLEBench+NorGLM: A Comprehensive Empirical Analysis and Benchmark Dataset for Generative Language Models in Norwegian (2024.emnlp-main)
Copied to clipboard
Peng Liu, Lemei Zhang, Terje Farup, Even Lauvrak, Jon Ingvaldsen, Simen Eide, Jon Atle Gulla, Zhirong Yang
| Challenge: | Norwegian is under-represented within the most impressive breakthroughs in NLP tasks. |
| Approach: | they investigate the impact of existing Norwegian language models on Norwegian generation tasks . they pre-trained 4 Norwegian Open Language Models from parameter scales and architectures . |
| Outcome: | The proposed benchmark evaluates the performance of language models on Norwegian generation tasks. |
Dual-teacher Knowledge Distillation for Low-frequency Word Translation (2024.findings-emnlp)
Copied to clipboard
| Challenge: | Neural machine translation models are trained on parallel corpora with unbalanced word frequency distribution, resulting in high-frequency words being ignored. |
| Approach: | They propose to employ a low-frequency teacher model that excels in translating low- frequency words to guide the learning of the student model. |
| Outcome: | The proposed method achieves +0.64 BLEU improvements over the state-of-the-art method on the low-frequency translation task while maintaining the translation quality of high-frequency words. |
JGLUE: Japanese General Language Understanding Evaluation (2022.lrec-1)
Copied to clipboard
| Challenge: | There is no benchmark for Japanese to evaluate and analyze NLU ability from different perspectives. |
| Approach: | They build a Japanese NLU benchmark from scratch without translation to measure general NLU ability in Japanese. |
| Outcome: | a Japanese NLU benchmark is built from scratch without translation to measure general NLU ability in Japanese. |
Incorporating Noisy Length Constraints into Transformer with Length-aware Positional Encodings (2020.coling-main)
Copied to clipboard
| Challenge: | Neural Machine Translation suffers from an under-translation problem due to limited modeling of output sequence lengths. |
| Approach: | They propose a method to train a Transformer model using length constraints based on positional encoding. |
| Outcome: | The proposed method outperforms a vanilla Transformer in an English-to-Japanese translation by 3.22 points . the noise injection improved robustness for length prediction errors, especially within the window size. |
A Retrieve-and-Rewrite Initialization Method for Unsupervised Machine Translation (2020.acl-main)
Copied to clipboard
| Challenge: | Recent work shows successful methods for unsupervised machine translation (UMT) initialization stage is important since bad initialization may wrongly squeeze the search space and too much noise may hurt the final performance. |
| Approach: | They propose a retrieval and rewriting based method to better initialize unsupervised translation models. |
| Outcome: | The proposed method improves translation performance by over 4 BLEU scores. |
MGAD: Multilingual Generation of Analogy Datasets (L18-1)
Copied to clipboard
| Challenge: | Existing methods for word embedding evaluation are computationally expensive and task-specific. |
| Approach: | They propose a minimally supervised method for generating word embedding evaluation datasets for a large number of languages using existing dependency treebanks and parsers. |
| Outcome: | The proposed method evaluates three popular word embedding algorithms against these datasets and shows that their performance varies between syntactic categories. |
Probing Multi-modal Machine Translation with Pre-trained Language Model (2021.findings-acl)
Copied to clipboard
| Challenge: | Multi-modal machine translation (MMT) aimed at using images to help disambiguate the target during translation but recent studies showed that visual features are either negligible or incremental. |
| Approach: | They propose to incorporate a visual language model on the source side to improve multi-modal translation quality significantly. |
| Outcome: | The proposed model improves the translation quality significantly on the multi-modal dataset. |
Improving Speech Translation by Understanding and Learning from the Auxiliary Text Translation Task (2021.acl-long)
Copied to clipboard
| Challenge: | Pretraining and multitask learning are widely used to improve the speech translation performance. |
| Approach: | They propose to train a speech translation model along with an auxiliary text translation task. |
| Outcome: | The proposed method improves translation quality by more than 2 BLEU over a strong baseline and achieves state-of-the-art results on the MuST-C English-German, English-French and English-Spanish language pairs. |
Large Language Model for Multi-Domain Translation: Benchmarking and Domain CoT Fine-tuning (2024.findings-emnlp)
Copied to clipboard
| Challenge: | Achieving consistent high-quality machine translation across diverse domains remains a challenge due to limited and imbalanced parallel training data available in various domains. |
| Approach: | They propose a domain Chain of Thought technique that uses the multi-domain intelligence of LLMs to improve translation performance. |
| Outcome: | The proposed method achieves significant improvements in translation accuracy and domain robustness over traditional fine-tuning on a small dataset of four domains. |
Learning to Jointly Translate and Predict Dropped Pronouns with a Shared Reconstruction Mechanism (D18-1)
Copied to clipboard
| Challenge: | Pronouns are often omitted in pro-drop languages, such as Chinese . this leads to various translation problems in terms of completeness, syntax and semantics . |
| Approach: | They propose a reconstruction-based approach to alleviate dropped pronoun (DP) translation problems for neural machine translation models by employing a shared reconstructor and a joint learning approach. |
| Outcome: | The proposed approach improves translation performance and accuracy of DP predictions. |
Using Neural Machine Translation for Generating Diverse Challenging Exercises for Language Learner (2023.acl-long)
Copied to clipboard
| Challenge: | a common challenge for language learners is understanding how to appropriately use words that may have similar meanings but are used in different contexts. |
| Approach: | They propose a method to automatically generate distractors for cloze exercises for English language learners using round-trip neural machine translation. |
| Outcome: | The proposed method generates distractors for cloze exercises for English learners . it shows that the generated distractors are of the same difficulty as human distractors . |
Singlish Message Paraphrasing: A Joint Task of Creole Translation and Text Normalization (2022.coling-1)
Copied to clipboard
| Challenge: | Existing computational approaches to translate languages or creoles back to standard English are challenging . lexical level normalization, syntactic level editing, and semantic level rewriting are key to a successful translation task. |
| Approach: | They propose a computational task to parse Singlish into English using its dialects . they propose to use a dataset to normalize and edit the text to improve translation . |
| Outcome: | The proposed model can improve translation performance and improve stance detection. |
NeoAMT: Neologism-Aware Agentic Machine Translation with Reinforcement Learning (2026.acl-long)
Copied to clipboard
| Challenge: | Neologism-aware machine translation aims to translate source sentences containing neologismes into target languages. |
| Approach: | They propose an agentic framework for neologism-aware machine translation equipped with a Wiktionary-based search toolkit. |
| Outcome: | The proposed framework is based on a Wiktionary-based search toolkit and a dedicated dataset for neologism-aware machine translation. |
When Does Monolingual Data Help Multilingual Translation: The Role of Domain and Model Scale (2024.naacl-long)
Copied to clipboard
| Challenge: | Multilingual machine translation (MMT) is a key tool for improving translation in low-resource languages. |
| Approach: | They examine how denoising autoencoding and backtranslation impact multilingual machine translation under different data conditions and model scales. |
| Outcome: | The proposed method improves translation efficiency in low-resource languages by using denoising autoencoding (DAE) and backtranslation (BT) . |
How Robust Are Router-LLMs? Analysis of the Fragility of LLM Routing Capabilities (2026.eacl-long)
Copied to clipboard
| Challenge: | Large language model (LLM) routing has emerged as a promising solution to balancing computational costs and performance. |
| Approach: | They propose a framework that categorizes router performance across a broad spectrum of query types . large language models have revolutionized natural language processing . |
| Outcome: | The proposed framework categorizes router performance across a broad spectrum of query types . it integrates privacy and safety assessments to reveal hidden risks . |
DART: Disambiguation-Aware Reasoning for Video-guided Machine Translation (2026.acl-long)
Copied to clipboard
| Challenge: | Video-guided Machine Translation (VMT) uses short video clips to enhance translation quality, but many samples are text-sufficient. |
| Approach: | They propose a framework that integrates multimodal large language models’ multimodal reasoning into video-guided machine translation by using a pipeline for constructing training data based on multimodal relevance to translation. |
| Outcome: | The proposed framework improves multimodal information utilization in video-guided machine translation, yielding gains in translation quality and computational efficiency. |
Norm-based Noisy Corpora Filtering and Refurbishing in Neural Machine Translation (2022.emnlp-main)
Copied to clipboard
| Challenge: | Existing noisy corpora filtering methods are insufficient to solve this problem, requiring multiple scorers trained on clean bitexts. |
| Approach: | They propose to use the information ratio from the source to the target side to distinguish unparallel sentence pairs by using norms of context vectors. |
| Outcome: | The proposed method performs comparably with state-of-the-art noisy corpora filtering techniques but is more efficient and easier to operate. |
MultiMWE: Building a Multi-lingual Multi-Word Expression (MWE) Parallel Corpora (2020.lrec-1)
Copied to clipboard
| Challenge: | Existing bilingual or multi-lingual MWE corpora are limited for multilingual use . only 871 pairs of English-German MWEs are available for research . |
| Approach: | They present a collection of bilingual and multi-lingual MWEs extracted from parallel corpora. |
| Outcome: | The available bilingual or multi-lingual MWE corpus is very limited . the collection is a small collection of 871 pairs of English-German MWEs . |
Distilling Multiple Domains for Neural Machine Translation (2020.emnlp-main)
Copied to clipboard
| Challenge: | Neural machine translation is a powerful tool for high-resource domains, but performance suffers when the input domain is low-resourced. |
| Approach: | They propose a framework for training a single multi-domain neural machine translation model that can translate multiple domains without increasing inference time or memory usage. |
| Outcome: | The proposed model improves translation on both high- and low-resource domains over strong multi-domain baselines and is robust under noisy data conditions. |
INSTRUCTSCORE: Towards Explainable Text Generation Evaluation with Automatic Feedback (2023.emnlp-main)
Copied to clipboard
| Challenge: | Existing methods to evaluate the quality of language generation do not provide explicit explanation of their verdicts. |
| Approach: | They propose a fine-grained explainable evaluation metric for text generation that harnesses human instruction and implicit knowledge of GPT-4 to fine-tune it. |
| Outcome: | The proposed model outperforms all other unsupervised metrics on translation, captioning, data-to-text, and commonsense generation tasks. |
GWLAN: General Word-Level AutocompletioN for Computer-Aided Translation (2021.acl-long)
Copied to clipboard
| Challenge: | Computer-aided translation (CAT) is a form of software that assists a human translator in the translation process. |
| Approach: | They propose to use computer-aided translation (CAT) to assist a human translator in the translation process. |
| Outcome: | The proposed method can give significantly more accurate predictions than baseline methods on CAT datasets. |
Reference Language based Unsupervised Neural Machine Translation (2020.findings-emnlp)
Copied to clipboard
| Challenge: | Existing approaches to use a common language as an auxiliary for better translation have a long tradition in machine translation. |
| Approach: | They propose a reference language-based framework for unsupervised neural machine translation that uses only one auxiliary language as an auxiliary for better translation. |
| Outcome: | The proposed framework improves the quality of pivot translation over a baseline that uses only one auxiliary language. |
Few-Shot Pidgin Text Adaptation via Contrastive Fine-Tuning (2022.coling-1)
Copied to clipboard
| Challenge: | Currently, low resource languages are not supported by proper translation systems or parallel corpus. |
| Approach: | They propose to fine-tune the pretrained language models to generate utterances in English-to-Pidgin by leveraging the proximity of the source and target languages and using positive and negative examples in constrastive training objectives. |
| Outcome: | The proposed method is sufficient to generate utterances in English-to-Pidgin, which are two closely-related languages. |
SimLex-999 for Polish (L18-1)
Copied to clipboard
| Challenge: | a linguistic evaluation tool is needed for distributional semantics tasks. |
| Approach: | They extend the Polish version of SimLex-999 to include measurement of similarity and relatedness. |
| Outcome: | The proposed model is compared with distributional semantics models for other languages. |
Unifying Input and Output Smoothing in Neural Machine Translation (2020.coling-main)
Copied to clipboard
| Challenge: | Recent methods that smooth input and output of neural machine translation systems bring significant improvements in performance. |
| Approach: | They propose a method that replaces one-hot representations with soft posterior distributions of an external language model, smoothing the input of machine translation systems. |
| Outcome: | The proposed method improves translation performance on small datasets and larger datasets. |
Long-Range Modeling of Source Code Files with eWASH: Extended Window Access by Syntax Hierarchy (2021.emnlp-main)
Copied to clipboard
Colin Clement, Shuai Lu, Xiaoyu Liu, Michele Tufano, Dawn Drain, Nan Duan, Neel Sundaresan, Alexey Svyatkovskiy
| Challenge: | Statistical language modeling and translation with transformers have found many successful applications in program understanding and generation tasks. |
| Approach: | They propose an architecture-independent approach for leveraging syntactic hierarchies of source code . they use syntax trees to extract syntak hierarchical structures and integrate them into context window . |
| Outcome: | The proposed approach achieves state-of-the-art in code completion and summarization for Python in the CodeXGLUE benchmark. |
CCSRD: Content-Centric Speech Representation Disentanglement Learning for End-to-End Speech Translation (2023.findings-emnlp)
Copied to clipboard
| Challenge: | Existing speech-to-text translation models can extract features from speech inputs, but they may include non-linguistic speech factors such as pitch, timbre and speaker identity. |
| Approach: | They propose a content-centric speech representation disentanglement learning framework for speech translation that decomposes speech representations into content representations and non-linguistic representations via representation disentanglement learning. |
| Outcome: | The proposed framework outperforms state-of-the-art speech translation models and cascaded models on five translation directions. |
Self-Distillation for Model Stacking Unlocks Cross-Lingual NLU in 200+ Languages (2024.findings-emnlp)
Copied to clipboard
| Challenge: | Large Language Models (LLMs) excel on English NLU tasks, yet struggle to extend their NLU capabilities to underrepresented languages. |
| Approach: | They integrate machine translation models (MT) directly into LLM backbones via sample-efficient self-distillation. |
| Outcome: | The proposed model outperforms translation-test models on 127 low-resource languages. |
Leveraging Discourse Rewards for Document-Level Neural Machine Translation (2020.coling-main)
Copied to clipboard
| Challenge: | Document-level machine translation models are often not trained to explicitly ensure discourse quality. |
| Approach: | They propose a method that explicitly optimizes lexical cohesion and coherence metrics by using a reinforcement learning objective. |
| Outcome: | The proposed approach improves document translations over four different languages and three translation domains while maintaining faithfulness to the reference translation. |
Large Language Models for Persian-English Idiom Translation (2025.naacl-long)
Copied to clipboard
| Challenge: | Large language models have shown superior capabilities in translating figurative language compared to neural machine translation systems. |
| Approach: | They evaluate LLMs, NMTs and their combinations using PersianIdioms datasets . they find that automatic evaluation methods like BLEU and BERTScore are effective . |
| Outcome: | The proposed model performs better in both directions than other models. |
Zero-Shot Crosslingual Sentence Simplification (2020.emnlp-main)
Copied to clipboard
| Challenge: | Recent approaches to simplification have shown promising results with encoder-decoder models trained on large amounts of parallel data which often only exists in English. |
| Approach: | They propose a model which transfers simplification knowledge from English to another language while generalizing across languages and tasks. |
| Outcome: | Empirical results show that the proposed model performs better than unsupervised and pivot-based methods. |
How to Learn in a Noisy World? Self-Correcting the Real-World Data Noise in Machine Translation (2025.findings-naacl)
Copied to clipboard
| Challenge: | Semantic misalignment, as the primary source of the noise, poses a challenge for training machine translation systems. |
| Approach: | They propose a process for simulating misalignment controlled by semantic similarity which closely resembles misaligned sentences in real-world web-crawled corpora. |
| Outcome: | The proposed model significantly improves translation performance in the presence of misalignment noise and when applied to real-world, noisy web-mined datasets, across a range of translation tasks. |
Representation Purification for End-to-End Speech Translation (2025.coling-main)
Copied to clipboard
| Challenge: | Existing approaches to enhance speech translation focus on enhancing knowledge transfer . factors in speech that are not relevant to translation content, such as timbre and rhythm, often limit the efficiency of knowledge transfer. |
| Approach: | They propose a framework that excludes content-agnostic perturbations from speech representations to mitigate their negative impact on ST. |
| Outcome: | The proposed framework significantly improves translation performance across all translation directions in three settings and achieves preeminent performance under a *transcript-free* setting. |
MSP: Multi-Stage Prompting for Making Pre-trained Language Models Better Translators (2022.acl-long)
Copied to clipboard
| Challenge: | Prompting has been shown to be a promising approach for applying pre-trained language models to perform downstream tasks. |
| Approach: | They propose a method that divides the translation process into three stages using pre-trained language models. |
| Outcome: | The proposed method significantly improves translation performance of pre-trained language models on three translation tasks. |
XLM-E: Cross-lingual Language Model Pre-training via ELECTRA (2022.acl-long)
Copied to clipboard
Zewen Chi, Shaohan Huang, Li Dong, Shuming Ma, Bo Zheng, Saksham Singhal, Payal Bajaj, Xia Song, Xian-Ling Mao, Heyan Huang, Furu Wei
| Challenge: | ELECTRA-style tasks are used to pretrain cross-lingual models for NLP tasks . masked language modeling tasks require massive computation resources, rendering such models quite expensive . |
| Approach: | They propose to use ELECTRA-style tasks to pre-train a cross-lingual language model . they propose to pretrain the model on multilingual and parallel corpora . |
| Outcome: | The proposed model outperforms baseline models on cross-lingual understanding tasks with much less computation cost. |
On the Sub-layer Functionalities of Transformer Decoder (2020.findings-emnlp)
Copied to clipboard
| Challenge: | Existing efforts to interpret the encoder of Transformer-based encoder-decoder architectures for neural machine translation have focused on assessing the encoded representations or interpreting the multi-head self-attentions. |
| Approach: | They propose to use Transformer-based encoder-decoder architectures to analyze how information is propagated through each module of each decoder layer. |
| Outcome: | The proposed model can be dropped with minimal loss of performance on three translation datasets and can be used to train and inference faster. |
Warmup Generations: A Task-Agnostic Approach for Guiding Sequence-to-Sequence Learning with Unsupervised Initial State Generation (2025.acl-long)
Copied to clipboard
| Challenge: | Existing supervised fine-tuning (SFT) methods focus on directly generating the target output without leveraging the benefits of intermediate steps or initial guidance. |
| Approach: | They propose a task-agnostic framework that enables models to generate intermediate "warmup" sequences that are iteratively refined to maximize their contribution to the final output. |
| Outcome: | The proposed framework outperforms traditional supervised fine-tuning methods on translation, summarization, and multi-choice question answering tasks. |
A Generalized Method for Automated Multilingual Loanword Detection (2022.coling-1)
Copied to clipboard
Abhijnan Nath, Sina Mahdipour Saravani, Ibrahim Khebour, Sheikh Mannan, Zihui Li, Nikhil Krishnaswamy
| Challenge: | Loanwords are words incorporated from one language into another without translation . authors present a method to automatically detect loanwords across language pairs . |
| Approach: | They propose a method to automatically detect loanwords across language pairs . they incorporate edit distance, semantic similarity measures, phonetic alignment . |
| Outcome: | The proposed method outperforms existing methods on single-pair loanword detection tasks and can generalize to unseen language pairs with sufficient data. |
Neural Machine Translation for Low-Resourced Indian Languages (2020.lrec-1)
Copied to clipboard
| Challenge: | Neural machine translation (NMT) is an effective way to convert text to a different language without human involvement. |
| Approach: | They propose to use multihead self-attention along with pre-trained Byte-Pair-Encoded (BPE) and MultiBPE embeddings to develop an efficient machine translation system. |
| Outcome: | The proposed system outperforms Google translator and the existing translators on two of the most morphological rich Indian languages. |
Informative Manual Evaluation of Machine Translation Output (2020.coling-main)
Copied to clipboard
| Challenge: | a new method for manual evaluation of machine translation output is proposed . evaluators mark problematic parts of the translated text, not just overall scores . |
| Approach: | They propose a method for manual evaluation of machine translation output based on marking actual issues in the translated text. |
| Outcome: | The proposed method can be applied on any genre/domain and language pair . it can be guided by various types of quality criteria and can be used for other types of generated text. |
Modeling Bilingual Conversational Characteristics for Neural Chat Translation (2021.acl-long)
Copied to clipboard
| Challenge: | Neural chat translation aims to translate bilingual conversational text due to its inherent characteristics such as role preference, dialogue coherence, and translation consistency. |
| Approach: | They propose to model the translation quality of conversational text by learning distributions of bilingual conversational characteristics. |
| Outcome: | The proposed approach outperforms baseline models and is widely available. |
Evaluation Dataset for Zero Pronoun in Japanese to English Translation (2020.lrec-1)
Copied to clipboard
| Challenge: | In natural language, we often omit some words that are easily understandable from the context. |
| Approach: | They propose to use a dataset to evaluate whether translation models can resolve zero pronoun problems in Japanese to English translations. |
| Outcome: | The proposed model can resolve the zero pronoun problem in Japanese to English translations. |
Coursera Corpus Mining and Multistage Fine-Tuning for Improving Lectures Translation (2020.lrec-1)
Copied to clipboard
| Challenge: | Lectures translation is a case of spoken language translation and there is nil available corpus for this purpose. |
| Approach: | They propose a framework for mining a parallel corpus from publicly available lectures at Coursera . they use machine translation and cosine similarity over continuous-space sentence representations to determine sentence alignments . |
| Outcome: | The proposed framework improves translation performance when used with out-of-domain parallel corpora . it also addresses noise in the mined data, and creates high-quality evaluation splits . |
PAEG: Phrase-level Adversarial Example Generation for Neural Machine Translation (2022.coling-1)
Copied to clipboard
| Challenge: | Existing methods for adversarial example generation are word-level or character-level, which ignore the ubiquitous phrase structure. |
| Approach: | They propose a phrase-level adversarial example generation framework to enhance the robustness of the translation model by adopting a sentence-level substitution strategy. |
| Outcome: | The proposed method improves translation performance and robustness to noise on three benchmarks. |
An Evaluation Benchmark for Testing the Word Sense Disambiguation Capabilities of Machine Translation Systems (2020.lrec-1)
Copied to clipboard
| Challenge: | Lexical ambiguity is one of the many challenging linguistic phenomena involved in translation, i.e., translating an ambiguous word with its correct sense. |
| Approach: | They propose to use training data to measure the sense distributions of a machine translation system to measure lexical ambiguity. |
| Outcome: | The proposed benchmark builds upon the multilingual sense inventory of BabelNet, the multilinguistic neural parsing pipeline TurkuNLP, and the OPUS collection of translated texts from the web. |
Interactive Post-Editing for Verbosity Controlled Translation (2022.coling-1)
Copied to clipboard
| Challenge: | Recent machine translation models have shown to excel with aspects of translation quality like adequacy and fluency but these models still suffer notable shortcomings like out-of-domain data, low-resource languages, rare words and longer sentences. |
| Approach: | They propose to use human-in-loop interactive post-editing models to improve translation quality and rephrase the text with a desired style variation. |
| Outcome: | The proposed model achieves BERTScore over state-of-the-art machine translation models while maintaining the desired token-level and verbosity preference. |
A Post-Editing Dataset in the Legal Domain: Do we Underestimate Neural Machine Translation Quality? (2020.lrec-1)
Copied to clipboard
Julia Ive, Lucia Specia, Sara Szoc, Tom Vanallemeersch, Joachim Van den Bogaert, Eduardo Farah, Christine Maroti, Artur Ventura, Maxim Khalilov
| Challenge: | Current state-of-the-art in Neural Machine Translation (NMT) has reached remarkable progress, but human evaluations are often judged as having lower quality than top NMT systems. |
| Approach: | They propose to use a machine translation dataset with post-edited high-quality neural machine translation and independent human references to compare the results. |
| Outcome: | The proposed dataset includes 31K tuples including a source sentence, the respective machine translation by a neural machine translation system, and a post-edited version of such translation by professional translator. |
MT3: A Synergistic Multi-Task RL Framework for Specializing MLLMs in Text Image Machine Translation (2026.acl-long)
Copied to clipboard
Zhaopeng Feng, Yupu Liang, Shaosheng Cao, Jiayuan Su, Jiahan Ren, Zhijie Zhou, Wenxuan Huang, Jian Wu, Zuozhu Liu
| Challenge: | Text Image Machine Translation (TIMT) is a critical subfield of machine translation . it requires accurate optical character recognition, robust visual-text reasoning, and high-quality translation a challenge . |
| Approach: | They propose a multi-task optimization framework to specialize MLLMs into expert TIMT models. |
| Outcome: | The proposed model outperforms baselines on the latest in-domain MIT-10M benchmark. |
Safety Alignment in NLP Tasks: Weakly Aligned Summarization as an In-Context Attack (2024.acl-long)
Copied to clipboard
| Challenge: | Recent developments in balancing usefulness and safety of large language models raise a critical question . current attacks, especially adversarial ones that manipulate malicious prompts, often aim to manipulate the input . |
| Approach: | They show that LLMs can effectively summarize malicious long documents but often refuse to translate them. |
| Outcome: | The findings highlight a vulnerability in LLMs that can't translate or summarize documents . the study focuses on LLM models, Gemini and GPT-4, which can' be exploited . |
Context-aware Decoder for Neural Machine Translation using a Target-side Document-Level Language Model (2021.naacl-main)
Copied to clipboard
| Challenge: | Neural machine translation models that incorporate inter-sentential contexts can be trained only in document-level parallel data with sentential alignments. |
| Approach: | They propose a method to perform context-aware decoding with any pre-trained translation model . their method uses sentence-level parallel data and target-side document-level monolingual data . |
| Outcome: | The proposed method performs context-aware decoding on English to Russian translation using BLEU and contrastive tests. |
Matina: A Large-Scale 73B Token Persian Text Corpus (2025.naacl-long)
Copied to clipboard
Sara Bourbour Hosseinbeigi, Fatemeh Taherinezhad, Heshaam Faili, Hamed Baghbani, Fatemeh Nadi, Mostafa Amiri
| Challenge: | Existing Persian datasets are small and lack content diversity . lack of high-quality data has slowed development of NLP models and open-source LLMs for Persian. |
| Approach: | They propose a Persian dataset of 72.9B tokens that is preprocessed and deduplicated to ensure high data quality. |
| Outcome: | The proposed model performs well on key Persian NLP tasks. |
Alleviating the Inequality of Attention Heads for Neural Machine Translation (2022.coling-1)
Copied to clipboard
| Challenge: | Recent studies show that the attention heads in Transformer are not equal. |
| Approach: | They propose a masking method to mask attention heads in Transformer . they empirically validate the inequality and propose 'head mask' method to avoid bottleneck . |
| Outcome: | The proposed masking method improves translation performance on multiple languages . it can be used to remove a small subset of heads without affecting performance . |
Towards Robust Neural Machine Translation with Iterative Scheduled Data-Switch Training (2022.coling-1)
Copied to clipboard
Zhongjian Miao, Xiang Li, Liyan Kang, Wen Zhang, Chulun Zhou, Yidong Chen, Bin Wang, Min Zhang, Jinsong Su
| Challenge: | Existing methods on robust neural machine translation (NMT) construct adversarial examples by injecting noise into authentic examples and indiscriminately exploit two types of examples. |
| Approach: | They propose an iterative scheduled data-switch training framework to mitigate this problem by injecting noise into authentic examples and indiscriminately exploiting two types of examples. |
| Outcome: | The proposed model outperforms several competitive benchmarks on four translation benchmarks. |
Simple Recurrent Units for Highly Parallelizable Recurrence (D18-1)
Copied to clipboard
| Challenge: | recurrent neural networks scale poorly due to the intrinsic difficulty in parallelizing their state computations. |
| Approach: | They propose a simple recurrent unit that provides expressive recurrence and allows highly parallel implementation. |
| Outcome: | The proposed model achieves 5—9x speed-up over cuDNN-optimized LSTM on classification and question answering datasets and delivers stronger results than LS and convolutional models. |
StreamSpeech: Simultaneous Speech-to-Speech Translation with Multi-task Learning (2024.acl-long)
Copied to clipboard
| Challenge: | Existing simultaneous translation methods focus on text-to-text and speech-totext translation. |
| Approach: | They propose a Simul-S2ST model that jointly learns translation and simultaneous policy in a unified framework of multi-task learning. |
| Outcome: | The proposed model can perform offline and simultaneous speech recognition, speech translation and speech synthesis via an "All-in-One" seamless model. |
Linear Cross-Lingual Mapping of Sentence Embeddings (2024.findings-acl)
Copied to clipboard
| Challenge: | Existing studies show that a sentence has less ambiguity than a single word . if the word semantics is changed in translation, then a better translation is possible. |
| Approach: | They propose a linear cross-lingual mapping to improve multilingual embeddings . they also consider deviation from orthogonality conditions as a measure of deficiency . |
| Outcome: | The proposed method improves the multilingual embeddings by allowing for a linear cross-lingual mapping. |
Selective Knowledge Distillation for Neural Machine Translation (2021.acl-long)
Copied to clipboard
| Challenge: | Neural Machine Translation models achieve state-of-the-art performance on many translation benchmarks. |
| Approach: | They propose a protocol that analyzes different impacts of samples by comparing various samples’ partitions. |
| Outcome: | The proposed methods yield up to +1.28 and +0.89 BLEU points improvements over the Transformer baseline, respectively. |
MTCue: Learning Zero-Shot Control of Extra-Textual Attributes by Leveraging Unstructured Context in Neural Machine Translation (2023.findings-acl)
Copied to clipboard
| Challenge: | Existing research has focused on providing individual, well-defined types of context in translation, such as the surrounding text or discrete external variables like the speaker’s gender. |
| Approach: | They introduce a novel neural machine translation framework that interprets all context as text. |
| Outcome: | The proposed framework outperforms a baseline that matched the parameters and significantly outperformed it in English translation. |
Mid-Air Hand Gestures for Post-Editing of Machine Translation (2021.acl-long)
Copied to clipboard
| Challenge: | In a well-connected world, translation is of everincreasing importance. |
| Approach: | They propose to use mid-air hand gestures in combination with the keyboard for editing in machine translation and post-editing workflows to improve quality. |
| Outcome: | The proposed prototype supports mid-air hand gestures for cursor placement, text selection, deletion, and reordering. |
Improving Neural Machine Translation with Soft Template Prediction (2020.acl-main)
Copied to clipboard
| Challenge: | Recent advances in neural machine translation (NMT) depend on source text to generate translation. |
| Approach: | They propose to use extracted templates from tree structures as soft target templates to guide the translation procedure. |
| Outcome: | The proposed model outperforms baseline models on four benchmarks and demonstrates the effectiveness of soft target templates. |
DivEMT: Neural Machine Translation Post-Editing Effort Across Typologically Diverse Languages (2022.emnlp-main)
Copied to clipboard
| Challenge: | Recent advances in neural language modeling and multilingual training have prompted widespread adoption of machine translation (MT) technologies across an unprecedented range of world languages. |
| Approach: | They propose to use a dataset to assess the impact of two state-of-the-art NMT systems, Google Translate and the multilingual mBART-50 model, on translation productivity. |
| Outcome: | The proposed model is faster than translation from scratch, but the magnitude of productivity gains varies widely across systems and languages. |
BigVideo: A Large-scale Video Subtitle Translation Dataset for Multimodal Machine Translation (2023.findings-acl)
Copied to clipboard
Liyan Kang, Luyang Huang, Ningxin Peng, Peihao Zhu, Zewei Sun, Shanbo Cheng, Mingxuan Wang, Degen Huang, Jinsong Su
| Challenge: | Existing datasets focus on captions describing images or videos, which are not large and diverse enough. |
| Approach: | They propose a large-scale video subtitle translation dataset to facilitate multi-modality machine translation. |
| Outcome: | The proposed dataset is 10 times larger than the widely used *How2* and *VaTeX* datasets. |
It Is Not As Good As You Think! Evaluating Simultaneous Machine Translation on Interpretation Data (2021.emnlp-main)
Copied to clipboard
| Challenge: | Existing siMT systems are trained and evaluated on offline translations . however, evaluation gap remains notable, calling for constructing large-scale interpretation corpora . |
| Approach: | They propose a translation-to-interpretation transfer method which converts offline translations into interpretation-style data. |
| Outcome: | The proposed interpretation test set shows that SiMT models improve on translation vs interpretation data. |
POMP: Probability-driven Meta-graph Prompter for LLMs in Low-resource Unsupervised Neural Machine Translation (2024.acl-long)
Copied to clipboard
| Challenge: | Low-resource languages (LRLs) face challenges in supervised neural machine translation due to limited parallel data. |
| Approach: | They propose a method that uses a dynamic graph to organize auxiliary languages in prompts to improve LRL translations. |
| Outcome: | The proposed method improves translation accuracy in low-resource languages (LRLs) using auxiliary language pairs and synthetic pseudo-parallel data. |
Is It Good Data for Multilingual Instruction Tuning or Just Bad Multilingual Evaluation for Large Language Models? (2024.emnlp-main)
Copied to clipboard
| Challenge: | Existing practices of fine-tuning and evaluating multilingual large language models may not align with this objective due to a heavy reliance on translation. |
| Approach: | They propose to use translated or native instruction data to fine-tune multilingual large language models. |
| Outcome: | The proposed model can be fine tuned and evaluated in multilingual large language models . the results show that native or translated data can be used to compare model performance . |
Learning Adaptive Segmentation Policy for End-to-End Simultaneous Translation (2022.acl-long)
Copied to clipboard
| Challenge: | Existing methods to perform simultaneous speech-to-text translation ignore contextual information and suffer from low translation quality. |
| Approach: | They propose an adaptive segmentation policy for simultaneous speech-to-text translation . it learns to segment the source streaming speech into meaningful units . |
| Outcome: | The proposed method achieves a good accuracy-latency trade-off over state-of-the-art methods on English-German and Chinese-English. |
Unlocking Memorization in Large Language Models with Dynamic Soft Prompting (2024.emnlp-main)
Copied to clipboard
Zhepeng Wang, Runxue Bao, Yawen Wu, Jackson Taylor, Cao Xiao, Feng Zheng, Weiwen Jiang, Shangqian Gao, Yanfu Zhang
| Challenge: | Pretrained large language models excel in a variety of natural language processing tasks . however, they pose significant security risks due to their tendency to memorize training data . |
| Approach: | They propose a method to estimate LLM memorization using dynamic, prefix-dependent soft prompts. |
| Outcome: | The proposed method can achieve maximum relative improvement of 135.3% and 39.8% over baseline compared to state-of-the-art methods. |
Extracting an English-Persian Parallel Corpus from Comparable Corpora (L18-1)
Copied to clipboard
| Challenge: | Existing methods to extract parallel sentences from Wikipedia are limited for some language pairs such as Persian-English. |
| Approach: | They propose a bidirectional method to extract parallel sentences from Wikipedia . they add extracted sentences to existing training data and use IR system to measure similarity . |
| Outcome: | The proposed method outperforms the one-directional approach in analyzing translation data from two translation systems and IR systems. |
Low-Resource Language Expansion and Translation Capacity Enhancement for LLM: A Study on the Uyghur (2025.coling-main)
Copied to clipboard
Kaiwen Lu, Yating Yang, Fengyi Yang, Rui Dong, Bo Ma, Aihetamujiang Aihemaiti, Abibilla Atawulla, Lei Wang, Xi Zhou
| Challenge: | Extensive experiments have shown that our strategy effectively expands the low-resource languages supported by large language models and significantly enhances the model’s translation ability in Uyghur with less parallel data. |
| Approach: | They propose a direct preference optimization based on translation self-evolution to expand low-resource languages into large language models by using Uyghur as an example. |
| Outcome: | The proposed strategy expands low-resource languages supported by large language models and significantly enhances the model’s translation ability in Uyghur with less parallel data. |
Large Language Models Can Learn Temporal Reasoning (2024.acl-long)
Copied to clipboard
| Challenge: | Temporal reasoning (TR) is a fundamental ability of large language models (LLMs) however, there is neo-standard methods to perform TR, which are not suitable for large language model applications. |
| Approach: | They propose a framework to enhance temporal reasoning by using a latent representation, temporal graph (TG) instead of reasoning over the original context, they adopt a temporal representation that enhances TR learning. |
| Outcome: | The proposed framework improves the learning of language-based TR by incorporating a latent representation, temporal graph (TG) a synthetic dataset is constructed for fine-tuning LLMs on text-to-TG translation tasks and benchmarks. |
Domain-Aware k-Nearest-Neighbor Knowledge Distillation for Machine Translation (2024.findings-acl)
Copied to clipboard
| Challenge: | Existing methods to transfer knowledge from kNN datastore into new models are expensive and arbitrarily transfer knowledge. |
| Approach: | They propose a domain-aware method which filters out domain-relevant neighborhood knowledge for learning in the distillation process. |
| Outcome: | The proposed method achieves state-of-the-art on four domain translation tasks. |
Evaluating Code-Switching Translation with Large Language Models (2024.lrec-main)
Copied to clipboard
| Challenge: | Recent advances in large language models (LLMs) have shown they can match or surpass finetuned models on many natural language processing tasks. |
| Approach: | They propose to use in-context learning and pivot translation to improve code-switching translation. |
| Outcome: | The proposed models show strong ability for cross-lingual understanding in a code-switching setting. |
Quick Back-Translation for Unsupervised Machine Translation (2023.findings-emnlp)
Copied to clipboard
| Challenge: | Unsupervised machine translation models are limited by the run-time of autoregressive inference during back-translation and lack of synthetic data efficiency. |
| Approach: | They propose a two-for-one improvement to Transformer back-translation: Quick Back-Translation (QBT). QBT re-purposes the encoder as a generative model, and uses encoder-generated sequences to train the decoder. |
| Outcome: | Experiments on various WMT benchmarks show that QBT dramatically outperforms standard back-translation only method in terms of training efficiency for comparable translation qualities. |
Data Doping or True Intelligence? Evaluating the Transferability of Injected Knowledge in LLMs (2025.findings-emnlp)
Copied to clipboard
| Challenge: | a study shows that comprehension-intensive fine-tuning tasks retain knowledge longer . however, all models exhibit significant performance drops when applying injected knowledge in broader contexts . |
| Approach: | study: comprehension-intensive fine-tuning tasks achieve higher knowledge retention rates . larger models show improved retention across all task types, study finds . |
| Outcome: | a new study shows that comprehension-intensive fine-tuning tasks retain knowledge better than mapping-oriented tasks despite exposure to identical factual content. |
Literality and cognitive effort: Japanese and Spanish (L18-1)
Copied to clipboard
| Challenge: | pause-word ratios are indicators of cognitive effort during different translation modalities. |
| Approach: | They propose a notion of pause-word ratio computed using ranges of a pause length rather than lower cutoffs for pauses . they compare translation and post-editing for language pairs that are different in terms of semantic and syntactic remoteness . |
| Outcome: | The proposed pause-word ratio measures cognitive effort in translation and post-editing for language pairs that are different in terms of semantic and syntactic remoteness. |
Reducing Word Omission Errors in Neural Machine Translation: A Contrastive Learning Approach (P19-1)
Copied to clipboard
| Challenge: | Existing methods for reducing word omission errors in neural machine translation are prone to omit essential words on the source side. |
| Approach: | They propose a contrastive learning approach to reduce word omission errors in NMT by omitting words. |
| Outcome: | The proposed approach achieves better translation performance than baseline methods on Chinese-to-English, German-to English, and Russian-toEnglish translation tasks. |
PerCul: A Story-Driven Cultural Evaluation of LLMs in Persian (2025.naacl-long)
Copied to clipboard
Erfan Moosavi Monazzah, Vahid Rahimzadeh, Yadollah Yaghoobzadeh, Azadeh Shakery, Mohammad Taher Pilehvar
| Challenge: | Large language models predominantly reflect Western cultures due to the dominance of English-centric training data. |
| Approach: | They propose a dataset to assess the sensitivity of LLMs to Persian culture. |
| Outcome: | The proposed model shows a 11.3% gap between best closed-source model and layperson baseline while the gap increases to 21.3% by using the best open-weight model. |
LLaMAX: Scaling Linguistic Horizons of LLM by Enhancing Translation Capabilities Beyond 100 Languages (2024.findings-emnlp)
Copied to clipboard
| Challenge: | Large Language Models (LLMs) exhibit exceptional translation capabilities in high-resource language tasks, yet their effectiveness in low-resourced languages is suboptimal. |
| Approach: | They conduct extensive multilingual continual pre-training on the LLaMA series models and develop LLiMAX for translation support across more than 100 languages. |
| Outcome: | The proposed model achieves higher translation performance than existing open-source models and performs on-par with specialized translation model on the Flores-101 benchmark. |
Don’t Rank, Combine! Combining Machine Translation Hypotheses Using Quality Estimation (2024.acl-long)
Copied to clipboard
| Challenge: | Neural machine translation models estimate probabilities of target sentences given source sentences, but these estimates may not align with human judgments. |
| Approach: | They propose a method that synthesizes translations using a quality estimation metric . they compare it with beam search and recent reranking techniques . |
| Outcome: | The proposed method outperforms other methods in large language models and multilingual translation models. |
Centroid-Based Efficient Minimum Bayes Risk Decoding (2024.findings-acl)
Copied to clipboard
| Challenge: | Minimum Bayes risk (MBR) decoding requires quadratic time since it computes the expected score between a translation hypothesis and all reference translations. |
| Approach: | They propose a centroid-based MBR decoding method that clusters the translations in the feature space and calculates the expected score using the centroids of each cluster. |
| Outcome: | The proposed method outperforms vanilla MBR decoding in translation quality by up to 0.5 COMET in the WMT’22 EnJa, EnDe, EnZh, and WMT'23 Enja translation tasks. |
JWSign: A Highly Multilingual Corpus of Bible Translations for more Diversity in Sign Language Processing (2023.findings-emnlp)
Copied to clipboard
| Challenge: | Existing sign language datasets are limited and skewed towards high-income sign languages, mainly those from high-risk countries. |
| Approach: | They propose a large and highly multilingual dataset for sign language translation: JWSign. |
| Outcome: | The proposed dataset consists of 2,530 hours of Bible translations in 98 sign languages, featuring more than 1,500 individual signers. |
Where Visual Speech Meets Language: VSP-LLM Framework for Efficient and Context-Aware Visual Speech Processing (2024.findings-emnlp)
Copied to clipboard
| Challenge: | Visual speech processing requires context modeling due to the ambiguous nature of lip movements. |
| Approach: | They propose a framework to maximize the context modeling capability by bringing the power of LLMs. |
| Outcome: | The proposed framework maximizes the power of visual speech processing by bringing it to the forefront of the field. |
Statistical Analysis of Missing Translation in Simultaneous Interpretation Using A Large-scale Bilingual Speech Corpus (L18-1)
Copied to clipboard
| Challenge: | Various types of omissions have been described in simultaneous interpretation to improve interpretation quality or train interpreters. |
| Approach: | They analyze missing translations in simultaneous interpretations using a large-scale bilingual speech corpus. |
| Outcome: | The authors found that a high proportion of adverbs were missed in the translations . the authors suggest that omissions can be improved to improve interpretation quality . |
wav2vec-S: Adapting Pre-trained Speech Models for Streaming (2024.findings-acl)
Copied to clipboard
| Challenge: | Pre-trained speech models have advanced speech-related tasks, including speech recognition and translation. |
| Approach: | They propose a pre-trained speech model that incorporates modifications to ensure consistent speech representations during training and inference phases for streaming speech inputs. |
| Outcome: | The proposed model outperforms baseline models on speech recognition and translation tasks and achieves a superior balance between quality and latency. |
Preventing Author Profiling through Zero-Shot Multilingual Back-Translation (2021.emnlp-main)
Copied to clipboard
| Challenge: | Documents as short as a single sentence may reveal sensitive information about authors . style transfer is effective but a number of current methods cause a drop in down-stream utility . |
| Approach: | They propose a method to remove sensitive information from documents by multilingual back-translation using off-the-shelf translation models. |
| Outcome: | The proposed method lowers adversarial gender and race prediction by 22% while retaining 95% of original utility on downstream tasks. |
Multi-task Adversarial Attacks against Black-box Model with Few-shot Queries (2025.acl-long)
Copied to clipboard
| Challenge: | Existing adversarial text attacks rely on abundant access to shared internal features and numerous queries, limited to a single task type. |
| Approach: | They propose a black-box attack that exploits the transferability of adversarial texts . they use a deep-level substitute model trained in a plug-and-play manner for text classification . |
| Outcome: | The proposed attack can target multiple tasks with minimal perturbations . it can target commercial APIs, large language models, and image-generation models . |
SwiLTra-Bench: The Swiss Legal Translation Benchmark (2025.acl-long)
Copied to clipboard
Joel Niklaus, Jakob Merane, Luka Nenadic, Sina Ahmadi, Yingqiang Gao, Cyrill A. H. Chevalley, Claude Humbel, Christophe Gösken, Lorenzo Tanzi, Thomas Lüthi, Stefan Palombo, Spencer Poff, Boling Yang, Nan Wu, Matthew Guillod, Robin Mamié, Daniel Brunner, Julio Pereyra, Niko Grupen
| Challenge: | In Switzerland legal translation relies on legal experts who must be both legal experts and skilled translators—creating bottlenecks and impacting effective access to justice. |
| Approach: | They propose a multilingual benchmarking system that evaluates Swiss legal translation systems based on 180K aligned Swiss legal translator pairs . they show frontier models achieve superior translation performance across all document types while specialized translation systems excel specifically in laws but under-perform in headnotes. |
| Outcome: | The proposed model outperforms specialized models in laws but underperform in headnotes. |
Exploiting Target Language Data for Neural Machine Translation Beyond Back Translation (2024.findings-acl)
Copied to clipboard
| Challenge: | Neural Machine Translation (NMT) encounters challenges when translating in new domains and low-resource languages. |
| Approach: | They propose a variant of k-nearest neighbor machine translation that utilizes target language data by constructing a pseudo datastore. |
| Outcome: | The proposed method exhibits strong domain adaptation capability in both high-resource and low-resourced machine translation. |
ParaCodex: A Profiling-Guided Autonomous Coding Agent for Reliable Parallel Code Generation and Translation (2026.acl-long)
Copied to clipboard
| Challenge: | Parallel programming is central to modern highperformance computing, but producing parallel implementations that are correct and fast remains arduous. |
| Approach: | They propose a workflow that turns a Codex-based agent into an autonomous OpenMP GPU offload system . they use staged hotspot analysis, explicit data planning, correctness gating, profiling-guided refinement . |
| Outcome: | The proposed system outperforms a Codex-based agent on HeCBench, Rodinia, and NAS. |
Predicting Human Translation Difficulty Using Automatic Word Alignment (2023.findings-acl)
Copied to clipboard
| Challenge: | Translation difficulty is a problem when translators are required to resolve translation ambiguity from multiple possible translations. |
| Approach: | They use word alignments computed over large scale bilingual corpora to develop predictors of lexical translation difficulty. |
| Outcome: | The proposed method improves on a previous embedding-based approach and can contribute to a deeper understanding of cross-lingual differences and of causes of translation difficulty. |
Identifying Source Language Expressions for Pre-editing in Machine Translation (2024.lrec-main)
Copied to clipboard
| Challenge: | MT-mediated communication can benefit from pre-editing source language texts to ensure accurate transmission of intended meaning in the target language. |
| Approach: | They hypothesize that such expressions tend to be distinctive features of texts originally written in the source language rather than translations generated from the target language into the source languages. |
| Outcome: | The proposed method identified characteristic expressions of the native language despite the noise and inherent nuances of the task. |
Language Model Priors and Data Augmentation Strategies for Low-resource Machine Translation: A Case Study Using Finnish to Northern Sámi (2024.findings-acl)
Copied to clipboard
| Challenge: | a new study examines the use of monolingual data for improving low-resource machine translation. |
| Approach: | They investigate ways of using monolingual data for improving low-resource machine translation. |
| Outcome: | The proposed model can perform better on the target-side data without augmentation of parallel data. |
Evaluating Factuality in Cross-lingual Summarization (2023.findings-acl)
Copied to clipboard
| Challenge: | Existing evaluation metrics for monolingual summarization require translation to evaluate the factuality of cross-lingual summmarization. |
| Approach: | They propose to analyze cross-lingual factuality by collecting annotations and generated summaries from models at summary level and sentence level. |
| Outcome: | The proposed dataset shows that over 50% of generated summaries contain factual errors with different characteristics from monolingual summarization. |
Contrastive Conditioning for Assessing Disambiguation in MT: A Case Study of Distilled Bias (2021.emnlp-main)
Copied to clipboard
| Challenge: | Lexical disambiguation is a major challenge for machine translation systems . previous work focused on automatic post-hoc analysis of translations, but rules of what makes a disambiguations correct or incorrect tend to be imprecise. |
| Approach: | They propose a black-box method that uses contrastive conditioning to detect disambiguation errors. |
| Outcome: | The proposed method is scalable and reliable for disambiguation evaluations. |
On Search Strategies for Document-Level Neural Machine Translation (2023.findings-acl)
Copied to clipboard
| Challenge: | Document-level neural machine translation models produce a more consistent output across a document . however, the exact decoding strategy is often not described and not mentioned at all. |
| Approach: | They propose to use standard automatic metrics and specific linguistic phenomena to compare different decoding schemes. |
| Outcome: | The proposed decoding strategies perform similar to each other on three standard document-level translation benchmarks. |
Implicit Memory Transformer for Computationally Efficient Simultaneous Speech Translation (2023.findings-acl)
Copied to clipboard
| Challenge: | Simultaneous speech translation is an essential communication task difficult for humans whereby a translation is generated concurrently with oncoming speech inputs. |
| Approach: | They propose a transformer that implicitly retains memory through a new left context method, removing the need to explicitly represent memory with memory banks. |
| Outcome: | The proposed method provides a substantial speedup on the encoder forward pass with nearly identical translation quality when compared with the state-of-the-art approach that uses left context and memory banks. |
Paying More Attention to Source Context: Mitigating Unfaithful Translations from Large Language Model (2024.findings-acl)
Copied to clipboard
| Challenge: | Large language models lack explicit alignment between source and target contexts, leading to unfaithful translations. |
| Approach: | They propose three learning strategies to encourage LLMs to pay more attention to source context . they use a dataset to test the effectiveness of their model across multiple language pairs . |
| Outcome: | The proposed model reduces hallucinatory translation and improves fidelity across multiple languages. |
Learning Language-Specific Layers for Multilingual Machine Translation (2023.acl-long)
Copied to clipboard
| Challenge: | Multilingual Machine Translation (MNMT) is a promising new approach to improve translation quality between non-English languages. |
| Approach: | They propose a language-specific transformer layer to increase model capacity while keeping computation and parameters constant. |
| Outcome: | The proposed approach improves translation quality by 1.3 chrF (1.5 spBLEU) over not using LSLs on a separate decoder architecture. |
Khan Academy Corpus: A Multilingual Corpus of Khan Academy Lectures (2024.lrec-main)
Copied to clipboard
| Challenge: | a dataset of 10122 hours in 87394 recordings is presented in a new journal . 43% of recordings have human-written subtitles, covering a total of 137 languages. |
| Approach: | They present a Khan Academy corpus with 10122 hours in 87394 recordings . 43% of recordings have human-written subtitles, and 137 languages are included . |
| Outcome: | The dataset can be used to train multilingual speech recognition and translation models. |
Ladder: A Model-Agnostic Framework Boosting LLM-based Machine Translation to the Next Level (2024.emnlp-main)
Copied to clipboard
| Challenge: | General-purpose Large Language Models (LLMs) like GPT-4 have exhibited strong translation abilities. |
| Approach: | They propose to use a model-agnostic model to refine the performance of general-purpose large-language models for machine translation (MT) by utilizing Gemma-2B/7B as the backbone. |
| Outcome: | The proposed model-agnostic and cost-effective tool improves the performance of general-purpose large-language models for machine translation (MT) by integrating it with any general-use LLM. |
Finding the Optimal Byte-Pair Encoding Merge Operations for Neural Machine Translation in a Low-Resource Setting (2024.findings-emnlp)
Copied to clipboard
| Challenge: | Using different byte pair encoder configurations, we can improve neural machine translation performance for low-resource languages. |
| Approach: | They investigate the impact of different Byte Pair Encoding configurations on neural machine translation performance for the Filipino-Cebuano language pair across various text domains. |
| Outcome: | The proposed methods show that smaller BPE configurations yield higher BLEU scores, indicating improved translation quality through finer tokenization granularity . larger BPE setups and the absence of BPE result in lower BLUE scores, suggesting a decline in translation quality due to coarser tokenisation. |
LLM-based Translation Inference with Iterative Bilingual Understanding (2025.findings-acl)
Copied to clipboard
| Challenge: | Existing studies show that the ability of large language models to generate contextual understanding of the sentence can degrade translation quality. |
| Approach: | They propose a method that generates contextual understanding for both source and target languages separately. |
| Outcome: | The proposed method outperforms strong comparison methods in multiple domains. |
LIMIT: Language Identification, Misidentification, and Translation using Hierarchical Models in 350+ Languages (2023.emnlp-main)
Copied to clipboard
| Challenge: | Currently, existing systems cannot accurately identify most of the world's 7000 languages due to lack of data and computational challenges. |
| Approach: | They propose a misprediction-resolution hierarchical model, LIMIT, that reduces error by 55% on a children's stories dataset and by 40% on 'fLORES-200' benchmark. |
| Outcome: | The proposed model reduces error by 55% on the MCS-350 and 40% on the FLORES-200 benchmarks. |
SpeechMatrix: A Large-Scale Mined Corpus of Multilingual Speech-to-Speech Translations (2023.acl-long)
Copied to clipboard
Paul-Ambroise Duquenne, Hongyu Gong, Ning Dong, Jingfei Du, Ann Lee, Vedanuj Goswami, Changhan Wang, Juan Pino, Benoît Sagot, Holger Schwenk
| Challenge: | SpeechMatrix is a large-scale multilingual corpus of speech-to-speech translations mined from real speech of European Parliament recordings. |
| Approach: | They present a large-scale multilingual corpus of speech-to-speech translations mined from real speech of European Parliament recordings. |
| Outcome: | The proposed model can train bilingual models on 136 language pairs with 418 thousand hours of speech. |
Can Multi-agent Help Disambiguation in Multi-domain Translation? (2026.findings-acl)
Copied to clipboard
| Challenge: | Existing multi-agent systems have shown strong potential for machine translation (MT) but their performance in multidomain translation remains unsatisfactory due to cross-domain word ambiguity . |
| Approach: | They propose a multi-agent collaborative disambiguation framework for MDT that leverages the collaborative capabilities of LLMs for disambiguations. |
| Outcome: | The proposed framework improves translation performance across multiple domains and improves disambiguation accuracy. |
Cost-Performance Optimization for Processing Low-Resource Language Tasks Using Commercial LLMs (2024.findings-emnlp)
Copied to clipboard
| Challenge: | Large Language Models (LLMs) exhibit impressive zero/few-shot inference and generation quality for high-resource languages (HRLs). |
| Approach: | They propose to reduce the cost of processing LRLs by code-mixing, translation, and transliteration of LRL to HRLs to ensure that predictive and generative qualities are not compromised. |
| Outcome: | The proposed model reduces the cost of processing LRLs while ensuring that predictive and generative qualities are not compromised. |
A Parallel Corpus for Vietnamese Central-Northern Dialect Text Transfer (2023.findings-emnlp)
Copied to clipboard
| Challenge: | Among these, the northern dialect is often treated as the standard i.e. the defacto text style of the language. |
| Approach: | They propose a parallel corpus for Vietnamese central-northern dialect text transfer to facilitate research on this domain. |
| Outcome: | The proposed model improves existing models on the central dialect domain with dedicated results in translation and text-image retrieval tasks. |
Nearest Neighbor Machine Translation is Meta-Optimizer on Output Projection Layer (2023.emnlp-main)
Copied to clipboard
| Challenge: | Nearest Neighbor Machine Translation (kNN-MT) is a powerful domain adaptation tool . the reasons for its success have not been thoroughly investigated . |
| Approach: | They propose to integrate pre-trained Neural Machine Translation models with token-level retrieval . they propose to implicitly execute gradient descent on the output projection layer of NMT . |
| Outcome: | The proposed approach outperforms model fine-tuning on in-domain tests while achieving better performance on out-of-domain sets. |
Improving Language and Modality Transfer in Translation by Character-level Modeling (2025.acl-long)
Copied to clipboard
| Challenge: | Current translation systems cover only 5% of the world's languages . expanding to the long-tail of low-resource languages requires data-efficient methods that rely on cross-lingual and cross-modal knowledge transfer. |
| Approach: | They propose a character-based approach to improve adaptability to new languages and modalities by using a teacher-student approach and parallel translation data to obtain a SONAR character-level encoder. |
| Outcome: | The proposed model outperforms subword-based models in speech-to-text translation on the FLEURS benchmark on 33 languages and achieves state-of-the-art generalizability to unseen languages. |
ParroT: Translating during Chat using Large Language Models tuned with Human Translation and Feedback (2023.findings-emnlp)
Copied to clipboard
Wenxiang Jiao, Jen-tse Huang, Wenxuan Wang, Zhiwei He, Tian Liang, Xing Wang, Shuming Shi, Zhaopeng Tu
| Challenge: | Large language models (LLMs) like ChatGPT are only accessible through restricted APIs, which creates barriers to new research and advancements in the field. |
| Approach: | They propose a framework to enhance and regulate the translation abilities during chat . they reformulate translation data into the instruction-following style and introduce a "Hint" field . |
| Outcome: | The proposed framework enhances and regulates the translation abilities during chat . it reformulates translation data into the instruction-following style and introduces a "Hint" field . |
Multilingual Coreference Resolution in Low-resource South Asian Languages (2024.lrec-main)
Copied to clipboard
| Challenge: | Existing coreference resolution models for South Asian languages are limited . a a sanity check for the prediction of translations is required to ensure accuracy of the model, authors say . |
| Approach: | They evaluate an end-to-end coreference resolution model on a Hindi golden set . they use translation and word-alignment tools to translate a translated dataset into 31 languages . |
| Outcome: | The proposed model scored 64 and 68 on a Hindi golden set. |
Document-Level Machine Translation with Large Language Models (2023.emnlp-main)
Copied to clipboard
| Challenge: | Large language models (LLMs) such as ChatGPT can produce coherent, cohesive, relevant, and fluent answers for various natural language processing tasks. |
| Approach: | They examine the impact of different prompts on document-level translation quality and discourse phenomena using figures and lines, which are invisible to GPT-4. |
| Outcome: | The proposed models outperform commercial MT systems and advanced document-level MT methods on a number of benchmarks and show potential to become a new paradigm for document- level translation. |
Target-Agnostic Gender-Aware Contrastive Learning for Mitigating Bias in Multilingual Machine Translation (2023.emnlp-main)
Copied to clipboard
| Challenge: | Gender bias is a significant issue in machine translation, but most studies focus on debiasing bilingual models without consideration for multilingual systems. |
| Approach: | They propose a method which debiases bilingual models for unambiguous cases where there is a single correct translation. |
| Outcome: | The proposed method improves gender accuracy by a wide margin without hampering translation performance. |
TransAlign: Machine Translation Encoders are Strong Word Aligners, Too (2025.findings-emnlp)
Copied to clipboard
| Challenge: | translation-based approaches to cross-lingual transfer (XLT) are limited. |
| Approach: | They propose a word aligner that utilizes the encoder of a massively multilingual MT model. |
| Outcome: | The proposed word aligner outperforms existing WA and state-of-the-art non-WA-based methods in token classification tasks. |
Who Watches the Watchmen? Humans Disagree With Translation Metrics on Unseen Domains (2026.findings-acl)
Copied to clipboard
| Challenge: | Existing studies that analyze unseen domains vary translation systems, annotators, or evaluation conditions, confounding domain effects with human annotation noise. |
| Approach: | They propose to use human error span annotations to evaluate translations of six translation systems across one seen news domain and two unseen technical domains to address these biases. |
| Outcome: | The proposed model improves on the human annotations in two unseen domains and on the news domains. |
Toward Global AI Inclusivity: A Large-Scale Multilingual Terminology Dataset (GIST) (2025.findings-acl)
Copied to clipboard
Jiarui Liu, Iman Ouzzani, Wenkai Li, Lechen Zhang, Tianyue Ou, Houda Bouamor, Zhijing Jin, Mona T. Diab
| Challenge: | Despite advances in machine translation, domain-specific terminology translation remains challenging. |
| Approach: | They propose a large-scale multilingual AI terminology dataset that combines LLMs for extraction with human expertise for translation. |
| Outcome: | The proposed framework combines human translation expertise with LLMs to improve translation accuracy and improve BLEU and COMET scores. |
Can Large Language Models Translate Unseen Languages in Underrepresented Scripts? (2025.emnlp-main)
Copied to clipboard
| Challenge: | Large language models (LLMs) have demonstrated impressive performance in machine translation, but struggle with unseen low-resource languages. |
| Approach: | They propose a benchmark to evaluate translation for Mongolian and Yi using linguistic resources. |
| Outcome: | The proposed model can translate Mongolian (in traditional script) and Yi with the help of linguistic resources, but is limited in its ability to handle these languages effectively. |
Can Code-Switched Texts Activate a Knowledge Switch in LLMs? A Case Study on English-Korean Code-Switching (2025.findings-emnlp)
Copied to clipboard
| Challenge: | Recent large language models (LLMs) demonstrate multilingual abilities, yet they are English-centric due to dominance of English in training corpora. |
| Approach: | They propose to use a synthetic English-korean CS question-answering dataset to investigate this potential. |
| Outcome: | The proposed model can activate, identify and leverage knowledge for reasoning in low-resource languages. |
Simul-MuST-C: Simultaneous Multilingual Speech Translation Corpus Using Large Language Model (2024.emnlp-main)
Copied to clipboard
| Challenge: | Simultaneous speech translation (SiST) begins translating before the entire source input is received. |
| Approach: | They propose a dataset that rearranges sentences into segmented monotonic data for simultaneous speech translation using the Large Language Model. |
| Outcome: | The proposed dataset improves quality and latency in siST translations by rearranging sentences into segmented monotonic data. |
COVER: Context-Driven Over-Refusal Verification in LLMs (2025.findings-acl)
Copied to clipboard
| Challenge: | Large Language Models (LLMs) have become increasingly prevalent in the field of Natural Language Processing (NLP), achieving unprecedented performance across linguistic tasks. |
| Approach: | They propose a framework to quantify and analyze context-driven over-refusal . they find that over-fusals depend on the task, system prompts, model family, and the number of retrieved documents. |
| Outcome: | The proposed framework quantifyes and analyzes the concept of context-driven over-refusal on two public corpora. |
Mina: A Multilingual LLM-Powered Legal Assistant Agent for Empowering Access to Justice in Bangladesh (2026.findings-acl)
Copied to clipboard
| Challenge: | Existing AI legal assistants lack Bengali-language support and jurisdiction-specific adaptation, limiting their effectiveness. |
| Approach: | They developed a multilingual LLM-based legal assistant tailored for the Bangladeshi context that employs multilingual embeddings and a RAG-based chain-of-tools framework for retrieval, reasoning, translation, and document generation. |
| Outcome: | Evaluated by law faculty from leading Bangladeshi universities across all stages of the 2022 and 2023 Bangladesh Bar Council examinations, Mina achieved scores of 75–80% in preliminary MCQs, written, and simulated viva voce components. |
OWL: Probing Cross-Lingual Recall of Memorized Texts via World Literature (2025.emnlp-main)
Copied to clipboard
Alisha Srivastava, Emir Kaan Korukluoglu, Minh Nhat Le, Duyen Tran, Chau Minh Pham, Marzena Karpinska, Mohit Iyyer
| Challenge: | Large language models (LLMs) are known to memorize and recall English text from their pretraining data, but the extent to which this ability generalizes to non-English languages or transfers across languages remains unclear. |
| Approach: | They propose a dataset of 31.5K aligned excerpts from 20 books in ten languages, including English originals, official translations and new translations in six low-resource languages. |
| Outcome: | The proposed model can recall English content in translations, but perturbations reduce performance, causing the model to fail. |
Exploring Context Strategies in LLMs for Discourse-Aware Machine Translation (2025.findings-emnlp)
Copied to clipboard
| Challenge: | Large language models excel at machine translation, but the impact of how LLMs utilize different forms of contextual information on discourse-level phenomena remains underexplored. |
| Approach: | They examine how different forms of context influence standard MT metrics and specific discourse phenomena such as formality, pronoun selection, and lexical cohesion. |
| Outcome: | Evaluating multiple LLMs across multiple domains and language pairs, the findings consistently show that context boosts translation and discourse-specific performance. |
Guaranteed Guess: A Language Modeling Approach for CISC-to-RISC Transpilation with Testing Guarantees (2025.findings-emnlp)
Copied to clipboard
| Challenge: | ISA-centric transpilation pipelines are used to translate low-level programs between ISAs . GG provides high code coverage across unit tests and better energy efficiency . |
| Approach: | They propose a ISA-centric transpilation pipeline that embeds large language models into software testing frameworks to ensure accuracy. |
| Outcome: | The proposed method achieves high code coverage across unit tests and functional/semantic correctness of 99% on HumanEval and 49% on BringupBench programs. |
BridG MT: Enhancing LLMs’ Machine Translation Capabilities with Sentence Bridging and Gradual MT (2025.findings-acl)
Copied to clipboard
| Challenge: | Recent Large Language Models (LLMs) have demonstrated impressive translation performance without the need for fine-tuning on additional parallel corpora. |
| Approach: | They propose a method that combines Sentence Bridging and Gradual MT to enhance LLMs' translation performance even outperforming translation methods that rely on a large number of few-shot examples. |
| Outcome: | The proposed method outperforms translation methods that rely on a large number of few-shot examples even when the source and target languages are low-resource languages. |
Synthetic Data Generation and Joint Learning for Robust Code-Mixed Translation (2024.lrec-main)
Copied to clipboard
| Challenge: | a number of languages are used in online conversations, resulting in code-mixing . the problem is largely unexplored due to the lack of annotated data and noise . |
| Approach: | They propose a robust perturbation-based joint-training model that learns to handle noise in code-mixed text by parameter sharing across clean and noisy words. |
| Outcome: | The proposed model learns to handle noise in the real-world code-mixed text by parameter sharing across clean and noisy words. |
Teaching Large Language Models to Translate on Low-resource Languages with Textbook Prompting (2024.lrec-main)
Copied to clipboard
| Challenge: | Large Language Models (LLMs) have demonstrated impressive results in Machine Translation by following instructions, even without training on parallel data. |
| Approach: | They propose a Translate After LEarNing Textbook approach which aims to enhance LLMs’ ability to translate low-resource languages by learning from a textbook. |
| Outcome: | The proposed approach improves translation performance by 14.8% using 112 low-resource languages from FLORES-200 with two LLMs: ChatGPT and BLOOMZ. |
TOWER+: Bridging Generality and Translation Specialization in Multilingual LLMs (2026.acl-long)
Copied to clipboard
Ricardo Rei, Nuno M Guerreiro, José Pombal, João Alves, Amin Farajian, Pedro Teixeirinha, Andre Martins
| Challenge: | Large Language Models (LLMs) are emerging as the de facto solution for multilingual machine translation. |
| Approach: | They propose a suite of LLMs that can be fine-tuned to deliver strong performance on translation and multilingual general-purpose text capabilities. |
| Outcome: | The proposed models outperform existing models on translation and general-purpose tasks. |
AFRIDOC-MT: Document-level MT Corpus for African Languages (2025.emnlp-main)
Copied to clipboard
Jesujoba Oluwadara Alabi, Israel Abebe Azime, Miaoran Zhang, Cristina España-Bonet, Rachel Bawden, Dawei Zhu, David Ifeoluwa Adelani, Clement Oyeleke Odoje, Idris Akinade, Iffat Maab, Davis David, Shamsuddeen Hassan Muhammad, Neo Putini, David O. Ademuyiwa, Andrew Caines, Dietrich Klakow
| Challenge: | AFRIDOC-MT is a document-level multi-parallel translation dataset covering five languages . AFRITIC-MT models perform better on sentences than general-purpose LLMs . |
| Approach: | They propose a document-level multi-parallel translation dataset covering English and five African languages. |
| Outcome: | The proposed dataset covers 334 health and 271 information technology news documents . it shows that NLLB-200 achieves the best average performance among standard models . |
Benchmarking Vision-Language Models on Chinese Ancient Documents: From OCR to Knowledge Reasoning (2026.findings-acl)
Copied to clipboard
Haiyang Yu, Yuchuan Wu, Fan Shi, Jinghui Lu, Ke Niu, Xiaodong Ge, Minghan Zhuo, Jingqun Tang, Bin Li
| Challenge: | Existing document benchmarks focus on English printed texts or simplified Chinese . current vision-language models struggle with visual complexity and poor adaptability . |
| Approach: | They propose a benchmark to evaluate Chinese ancient documents' visual/linguistic complexity . ancient documents are valuable cultural heritage, but they face challenges in digitization and understanding . |
| Outcome: | the first benchmark for Chinese ancient documents evaluates VLMs from OCR to knowledge reasoning . ancient documents carry thousands of years of Chinese history and culture . traditional methods only scan images, while current models struggle with visual complexity . |
Towards Robust In-Context Learning for Machine Translation with Large Language Models (2024.lrec-main)
Copied to clipboard
| Challenge: | Experimental results demonstrate the effectiveness of our method, particularly in domain adaptation. |
| Approach: | They propose a method to retrieve translation pairs as demonstrations from an additional datastore to guide translation without updating the LLMs. |
| Outcome: | The proposed method reduces noise and improves translation performance in domain adaptation. |
Utilizing Longer Context than Speech Bubbles in Automated Manga Translation (2024.lrec-main)
Copied to clipboard
Hiroto Kaino, Soichiro Sugihara, Tomoyuki Kajiwara, Takashi Ninomiya, Joshua B. Tanner, Shonosuke Ishiwatari
| Challenge: | Existing methods to capture contextual information for manga machine translation are difficult to perform . unofficially translated pirated copies of manga are circulating overseas in large numbers . |
| Approach: | They propose two new ways to capture broader contextual information in manga machine translation . scene-based translation considers previous scene and broader context information . detailed analysis reveals the effect of zero-anaphora resolution in translation - highlighting the usefulness of longer contextual information if manga is translated in Japanese . |
| Outcome: | The proposed methods improve translation quality for manga (Japanese-style comics) the results show that the combined methods achieve the highest quality. |
Towards Style Alignment in Cross-Cultural Translation (2025.acl-long)
Copied to clipboard
| Challenge: | Successful communication relies on the speaker’s intended style aligning with the listener’s interpreted style. |
| Approach: | They propose a method that leverages learned stylistic concepts to encourage LLM translation to appropriately convey cultural communication norms and align style. |
| Outcome: | The proposed method aims to encourage translations to convey cultural communication norms and align style. |
Just Go Parallel: Improving the Multilingual Capabilities of Large Language Models (2025.acl-long)
Copied to clipboard
| Challenge: | Large language models (LLMs) have impressive translation capabilities even without being explicitly trained on parallel data. |
| Approach: | They propose to add parallel data to enhance multilingual encoder-based and encoder decoder language models by focusing on translation and multilingual common-sense reasoning. |
| Outcome: | The proposed methods show that adding parallel data can significantly improve LLMs’ multilingual capabilities. |
EuroGEST: Investigating gender stereotypes in multilingual language models (2025.emnlp-main)
Copied to clipboard
| Challenge: | Large language models encode social biases, but most benchmarks for gender bias remain English-centric. |
| Approach: | They propose a dataset to measure gender-stereotypical reasoning in large language models across English and 29 European languages. |
| Outcome: | The proposed method is highly accurate across languages and strong in translations and gender labels. |
The Role of Mixed-Language Documents for Multilingual Large Language Model Pretraining (2026.acl-long)
Copied to clipboard
Jiandong Shao, Raphael Tang, Crystina Zhang, Karin Sevegnani, Pontus Stenetorp, Jianfei Yang, Yao Lu
| Challenge: | Existing research suggests that multilingual large language models can achieve impressive cross-lingual understanding despite largely monolingual pretraining. |
| Approach: | They compare a monolingual-only corpus with a standard web corpus that removes all multilingual documents and then retrain the models from scratch under controlled conditions. |
| Outcome: | The results show that removing bilingual data causes translation performance to drop 56% in BLEU, whereas code-switching contributes minimally. |
Just Use XML: Revisiting Joint Translation and Label Projection (2026.findings-acl)
Copied to clipboard
| Challenge: | Label projection is an effective technique for cross-lingual transfer, extending span-annotated datasets from high-resource languages to low-resourced ones. |
| Approach: | They propose a framework that performs translation and label projection via XML tags. |
| Outcome: | The proposed framework outperforms baselines and improves translation quality across languages and annotation complexity. |
Trojsten Benchmark: Evaluating LLM Problem-Solving in Slovak STEM Competition Problems (2025.emnlp-main)
Copied to clipboard
| Challenge: | Large language models have been used for grading open-ended responses and providing feedback beyond traditional methods. |
| Approach: | They propose a Slovak-language dataset and a rubric-based LLM grading framework . they quantify multistep reasoning performance by difficulty and show consistency under difficult items . |
| Outcome: | The proposed model outperforms existing models on Slovak-language competition problems . the model shows consistent underperformance on harder items and language sensitivity . |
Sign-Language Datasets at Scale: A Comprehensive Survey on Resources, Benchmarks, and Annotation Standards (2026.acl-long)
Copied to clipboard
| Challenge: | Existing benchmarks fail to reflect real-world communication needs and are limited in their coverage. |
| Approach: | They present a comprehensive index of sign-language datasets, covering 120 resources across 35 sign languages. |
| Outcome: | The proposed index covers 120 resources across 35 sign languages. |