Papers with BLEU
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. |
Answering Naturally: Factoid to Full length Answer Generation (D19-54)
Copied to clipboard
| Challenge: | Factoid question answering systems extract answers for a question from passages, which are usually short spans of text . but, these spans would result in an unnatural reading experience in a conversational system . a pointer generator based full-length answer generator can be used with most QA systems . |
| Approach: | They propose a pointer generator based full-length answer generator which can be used with most QA systems. |
| Outcome: | The proposed system generates full length answer without relying on passage from which it was extracted. |
Zero-Shot Cross-Lingual Transfer of Neural Machine Translation with Multilingual Pretrained Encoders (2021.emnlp-main)
Copied to clipboard
| Challenge: | Existing work on improving cross-lingual transferability of NMT model is under-explored. |
| Approach: | They propose a model that leverages a multilingual pretrained encoder to improve cross-lingual transferability. |
| Outcome: | The proposed model outperforms mBART and m2m-100 on a zero-shot cross-lingual transfer task. |
Context-Aware Neural Machine Translation Decoding (D19-65)
Copied to clipboard
| Challenge: | Existing approaches to enhance neural machine translation systems to take into account document-level information make the training process slower or require document- level annotated data. |
| Approach: | They propose a decoding architecture that fuses the semantic space language model and a neural translation model. |
| Outcome: | The proposed approach improves translation quality for English–Spanish using BLEU and METEOR. |
Domain Adaptation of Image Encoder for Multimodal Manga Translation (2026.eacl-srw)
Copied to clipboard
| Challenge: | Existing machine translation systems lack sufficient manga comprehension capabilities when utilizing image information. |
| Approach: | They propose a domain-adapted image encoder training method for manga . the method trains encoders to acquire visual features that consider the structural and sequential characteristics of the manga based on a Japanese-English translation task. |
| Outcome: | The proposed method improves translation evaluation metrics in Japanese-English translation task compared to the conventional method . |
Train, Sort, Explain: Learning to Diagnose Translation Models (N19-4)
Copied to clipboard
| Challenge: | Evaluating translation models is a trade-off between effort and detail. |
| Approach: | They propose to use a neural text classifier to automatically expose systematic differences between human and machine translations to human experts. |
| Outcome: | The proposed method exposes systematic differences between human and machine translations to human experts. |
Pre-Trained Multilingual Sequence-to-Sequence Models: A Hope for Low-Resource Language Translation? (2022.findings-acl)
Copied to clipboard
En-Shiun Lee, Sarubi Thillainathan, Shravan Nayak, Surangika Ranathunga, David Adelani, Ruisi Su, Arya McCarthy
| Challenge: | Pre-trained multilingual sequence-to-sequence models like mBART and mT5 can be used to translate low-resource languages, but their practical application is unclear. |
| Approach: | They conduct an empirical experiment in 10 languages to determine what can pre-trained multilingual sequence-to-sequence models like mBART do to translate low-resource languages? |
| Outcome: | The proposed models are robust to domain differences, but translations for unseen and typologically distant languages remain below 3.0 BLEU. |
Pre-training on high-resource speech recognition improves low-resource speech-to-text translation (N19-1)
Copied to clipboard
| Challenge: | Pre-training on high-resource automatic speech recognition (ASR) tasks improves ST performance even when source language is low-resourced. |
| Approach: | They propose a method to improve direct speech-to-text translation when source language is low-resource . they pre-train model on high-res automatic speech recognition task and fine-tune parameters for ST . |
| Outcome: | The proposed approach improves Spanish English ST even when the source language is low-resource . the pre-trained encoder accounts for most of the improvement, the authors show . |
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. |
Syntax-Based Attention Masking for Neural Machine Translation (2021.naacl-srw)
Copied to clipboard
| Challenge: | Existing approaches to extend transformers to source-side trees are linearized into sequences, but they are limited by positional encodings. |
| Approach: | They propose a method for extending transformers to source-side trees by using masks based on tree positions . they define a number of masks that limit self-attention based upon relationships among tree nodes . |
| Outcome: | The proposed method improves on translations from English to germany and English to english and germany by +2.1 BLEU. |
Simulated multiple reference training improves low-resource machine translation (2020.emnlp-main)
Copied to clipboard
| Challenge: | Existing valid translations for a given sentence are limited by a single reference translation, causing data sparsity in low-resource settings. |
| Approach: | They propose a method that approximates the full space of possible translations by sampling a paraphrase of the reference sentence from a MT model and training it to predict the paraphraser’s distribution over possible tokens. |
| Outcome: | The proposed method improves in low-resource settings and is complementary to back-translation. |
KNU-HYUNDAI’s NMT system for Scientific Paper and Patent Tasks onWAT 2019 (D19-52)
Copied to clipboard
Cheoneum Park, Young-Jun Jung, Kihoon Kim, Geonyeong Kim, Jae-Won Jeon, Seongmin Lee, Junseok Kim, Changki Lee
| Challenge: | We submitted our transformer-based neural machine translation system to the translation tasks of the 6th workshop on Asian Translation (WAT 2019). |
| Approach: | They propose a transformer-based neural machine translation system for Chinese-Japanese, English-Japanese, and Korean->Japanoise translation tasks. |
| Outcome: | The proposed system performed well on the two translation tasks and was ranked first in terms of the BLEU scores in all the JPC2 subtasks. |
A Partially Rule-Based Approach to AMR Generation (N19-3)
Copied to clipboard
| Challenge: | Abstract Meaning Representation (AMR) is a representation of a sentence as a labeled graph . because of these abstractions, it can be difficult to generate from AMR back to a fluent English sentence . |
| Approach: | They propose a new approach to generating English text from Abstract Meaning Representation (AMR) it is largely rule-based, supplemented by a language model and simple statistical linearization models . they also address difficulties of automatically evaluating AMR generation systems . |
| Outcome: | The proposed approach produces a fluent English sentence with a high quality . it is difficult to generate from an AMR back to a sentence which preserves original meaning . |
How Helpful is Inverse Reinforcement Learning for Table-to-Text Generation? (2021.acl-short)
Copied to clipboard
| Challenge: | Existing approaches to Table-to-Text generation suffer from issues such as missing information, repetition and repetition. |
| Approach: | They propose to use Inverse Reinforcement Learning (IRL) to solve the Table-to-Text task . they use multiple interpretable unsupervised reward components that are combined linearly to form a composite reward function. |
| Outcome: | The proposed task outperforms strong RL baselines marginally in the Table-to-Text task. |
Multimodal Machine Translation with Embedding Prediction (N19-3)
Copied to clipboard
| Challenge: | Pretrained word embeddings improve multimodal machine translation of low-resource domains due to a shortage of training data. |
| Approach: | They propose to combine pretrained word embeddings with search-based approaches to improve NMT of low-resource domains to better translate rare words. |
| Outcome: | The proposed approach improves translation performance by 1.24 METEOR and 2.49 BLEU and achieves 7.67 F-score. |
Facebook AI’s WAT19 Myanmar-English Translation Task Submission (D19-52)
Copied to clipboard
Peng-Jen Chen, Jiajun Shen, Matthew Le, Vishrav Chaudhary, Ahmed El-Kishky, Guillaume Wenzek, Myle Ott, Marc’Aurelio Ranzato
| Challenge: | Using back-translation, we can improve generalization by using noisy channel re-ranking and ensembling. |
| Approach: | They propose to use BPE-based transformer models to leverage monolingual data to improve generalization and use noisy channel re-ranking and ensembling to improve results. |
| Outcome: | The proposed system improves on the baseline system trained exclusively on the provided small parallel dataset, and the human evaluation and BLEU score are higher. |
The Importance of Being Parameters: An Intra-Distillation Method for Serious Gains (2022.emnlp-main)
Copied to clipboard
| Challenge: | Recent pruning methods remove redundant parameters according to parameter sensitivity, a gradient-based measure reflecting the contribution of the parameters. |
| Approach: | They propose a general task-agnostic method to balance parameter sensitivity and a novel adaptive learning method to control strength of intra-distillation loss for faster convergence. |
| Outcome: | The proposed method can reduce redundant parameters by over 80% without obvious performance degradation. |
Autocorrect in the Process of Translation — Multi-task Learning Improves Dialogue Machine Translation (2021.naacl-industry)
Copied to clipboard
| Challenge: | Existing neural machine translation models are not able to translate dialogues in real life scenarios. |
| Approach: | They propose a joint learning method to identify omission and typos and utilize context to translate dialogue utterances. |
| Outcome: | The proposed method improves translation quality by 3.2 BLEU over baselines and recovers omitted pronouns by 47.16%. |
Enhanced Transformer Model for Data-to-Text Generation (D19-56)
Copied to clipboard
| Challenge: | Neural models have shown significant progress on data-to-text generation tasks . data- to-text models generate descriptive texts from non-linguistic structured data . |
| Approach: | They propose a new data-to-text generation model which learns content selection and summary generation in an end-to end fashion. |
| Outcome: | The proposed model outperforms current state-of-the-art models on content selection precision and content ordering metrics. |
Vis-Eval Metric Viewer: A Visualisation Tool for Inspecting and Evaluating Metric Scores of Machine Translation Output (N18-5)
Copied to clipboard
| Challenge: | Many metrics have been proposed for Machine Translation (MT) that compare system translations against human references. |
| Approach: | They propose to use BLEU and METEOR to evaluate machine translations against human translations. |
| Outcome: | VisEval Metric Viewer (VEMV) provides visualisation of multiple evaluation scores so they can be easily interpreted by a user. |
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 Lexical Ability of Pretrained Language Models for Unsupervised Neural Machine Translation (2021.naacl-main)
Copied to clipboard
| Challenge: | Existing methods for unsupervised neural machine translation (UNMT) use cross-lingual pretraining to align the lexical- and high-level representations of two languages. |
| Approach: | They propose to use type-level cross-lingual subword embeddings to enhance the bilingual masked language model pretraining with lexical-level information to align the two languages. |
| Outcome: | Empirical results show that the method improves on UNMT (up to 4.5 BLEU) and bilingual lexicon induction compared to baseline models. |
Self-Vocabularizing Training for Neural Machine Translation (2025.naacl-srw)
Copied to clipboard
| Challenge: | Past vocabulary learning techniques identify relevant vocabulary before training, relying on corpus statistics or frequency counts without considering contextual information or the model's ability to represent it. |
| Approach: | They propose a method that self-vocabularizes a smaller, more optimal vocabulary by pairing source sentences with the model's predictions to define a new vocabulary. |
| Outcome: | The proposed method produces a 1.49 BLEU improvement in the simulated model and an increase in unique token usage and a 6–8% reduction in vocabulary size. |
Evaluating Question Answering Evaluation (D19-58)
Copied to clipboard
| Challenge: | Existing n-gram based QA metrics have a number of drawbacks and are not suitable for all extractive tasks. |
| Approach: | They propose to use BERTScore to evaluate translation for question answering (QA) they also explore whether existing n-gram based metrics are suitable for generative QA . |
| Outcome: | The proposed BERTScore metric fails to provide stronger correlation with human judgements . |
Neural Machine Translation without Embeddings (2021.naacl-main)
Copied to clipboard
| Challenge: | Existing models operate over subword tokens, but byte-based models employ a different approach . a one-hot representation of each byte does not hurt performance, but it improves BLEU scores . |
| Approach: | They propose to represent every computerized text as a sequence of bytes via UTF-8 . this eliminates the need for an embedding layer and improves performance . |
| Outcome: | The proposed model improves BLEU scores on byte-to-byte translation models compared to character-level models . the proposed model does not require an embedding layer and does not drop out of the decoder . |
CLIReval: Evaluating Machine Translation as a Cross-Lingual Information Retrieval Task (2020.acl-demos)
Copied to clipboard
| Challenge: | evaluating machine translation (MT) with cross-lingual information retrieval is relatively time-consuming and subjective. |
| Approach: | They propose a toolkit that evaluates machine translation with a proxy task of cross-lingual information retrieval. |
| Outcome: | The proposed toolkit is based on the "metrics shared task" of WMT2019. |
PePe: Personalized Post-editing Model utilizing User-generated Post-edits (2023.findings-eacl)
Copied to clipboard
| Challenge: | Existing neural machine translation models ignore personal style in their translations, but in these studies the definition of personal style is over-simplified. |
| Approach: | They propose a personalized automatic post-editing framework that generates sentences considering distinct personal behaviors by collecting post-edited data from a live machine translation system and combining a discriminator module and user-specific parameters. |
| Outcome: | The proposed model outperforms baseline models on four different metrics including BLEU, TER, YiSi-1, and human evaluation. |
Big Bidirectional Insertion Representations for Documents (D19-56)
Copied to clipboard
| Challenge: | Recent studies suggest we are nearing human-level parity for sentence-level translation in certain domains. |
| Approach: | They propose an insertion-based model for document-level translation tasks that embeds sentence alignment between the source and target document. |
| Outcome: | The proposed model improves on the WMT’19 English->German translation task by +4.3 BLEU compared with the Insertion Transformer baseline. |
GREEN: Generative Radiology Report Evaluation and Error Notation (2024.findings-emnlp)
Copied to clipboard
Sophie Ostmeier, Justin Xu, Zhihong Chen, Maya Varma, Louis Blankemeier, Christian Bluethgen, Arne Md, Michael Moseley, Curtis Langlotz, Akshay Chaudhari, Jean-Benoit Delbrouck
| Challenge: | Existing automated evaluation metrics fail to consider factual correctness or are limited in their interpretability. |
| Approach: | They propose a radiology report evaluation metric that leverages natural language understanding of language models to identify and explain clinically significant errors. |
| Outcome: | The proposed method demonstrates higher correlation with expert error counts and higher alignment with expert preferences when compared to previous methods. |
Improving Retrieval Augmented Neural Machine Translation by Controlling Source and Fuzzy-Match Interactions (2023.findings-eacl)
Copied to clipboard
| Challenge: | a general-domain model has access to customer or domain specific parallel data at inference time, but not during training. |
| Approach: | They propose a zero-shot adaptation approach where a general-domain model has access to customer or domain specific parallel data at inference time, but not during training. |
| Outcome: | The proposed architecture outperforms existing architectures in two language pairs . it consistently improves BLEU across language pair, domain, and number k of fuzzy matches . |
Learning Interpretable Latent Dialogue Actions With Less Supervision (2022.aacl-main)
Copied to clipboard
| Challenge: | supervised neural dialogue modeling requires a significant amount of work to obtain turn-level labels, usually with dialogue state annotation. |
| Approach: | They propose a novel architecture for explainable modeling of task-oriented dialogues with discrete latent variables to represent dialogue actions. |
| Outcome: | The proposed model outperforms previous approaches with less supervision in terms of perplexity and BLEU on three datasets. |
MR-P: A Parallel Decoding Algorithm for Iterative Refinement Non-Autoregressive Translation (2022.findings-acl)
Copied to clipboard
| Challenge: | Non-autoregressive neural machine translation models remove dependency between tokens in the target sentence and generate all tokens on parallel . |
| Approach: | They propose a non-autoregressive neural machine translation model that decodes with the Mask-Predict algorithm which iteratively refines the output. |
| Outcome: | The proposed algorithm increases the performance of the WMT’14 translation task by 1.39 points. |
Better Chinese Sentence Segmentation with Reinforcement Learning (2021.findings-acl)
Copied to clipboard
| Challenge: | Chinese-English machine translation systems use ambiguous sentence boundaries, but English and Chinese use different orthographic conventions to designate sentence boundaries. |
| Approach: | They propose a segmentation policy that splits Chinese texts into segments that can be independently translated to maximise translation quality. |
| Outcome: | The proposed method improves the baseline BLEU score on the Chinese-English news translation task by +0.3 BLUE overall and the score on input segments that contain more than 60 words by +3 BL EU. |
Learning Language Specific Sub-network for Multilingual Machine Translation (2021.acl-long)
Copied to clipboard
| Challenge: | Multilingual neural machine translation models suffer from performance degradation when learning multiple languages. |
| Approach: | They propose to use LaSS to jointly train a single unified multilingual MT model. |
| Outcome: | The proposed model gains on 36 language pairs by up to 1.2 BLEU and zero-shot translation with 8.3 BLUE on 30 language pairs. |
An Error Analysis Framework for Shallow Surface Realization (2021.tacl-1)
Copied to clipboard
| Challenge: | BLEU and METEOR metrics fail to provide information on which linguistic factors impact performance of natural language generation models. |
| Approach: | They propose a framework for error analysis which permits identifying which features of the input affect the models’ results. |
| Outcome: | The proposed framework improves the performance of 174 system runs submitted to the Multilingual SR shared tasks. |
Automating Human Evaluation of Dialogue Systems (2022.naacl-srw)
Copied to clipboard
| Challenge: | a recent study shows that human evaluations of dialogue systems weakly reflect human judgments. |
| Approach: | They propose a BERT-based model that fine-tunes a model with three prediction heads to predict whether the system-generated output is natural, fluent, and informative. |
| Outcome: | The proposed model achieves an average accuracy of 77% over the 3 labels . it also uses three different models to compute the labels compared to three separate models . |
Universal Neural Machine Translation for Extremely Low Resource Languages (N18-1)
Copied to clipboard
| Challenge: | a novel multilingual approach to machine translation is proposed for low resource languages . the proposed approach can achieve 23 BLEU on Romanian-English WMT2016 using a tiny parallel corpus of 6k sentences compared to the 18 BLUE of strong baseline system . |
| Approach: | They propose a transfer-learning approach to share lexical and sentence representations across multiple source languages into one target language. |
| Outcome: | The proposed approach achieves 23 BLEU on Romanian-English WMT2016 using a tiny parallel corpus of 6k sentences compared to the 18 BLUE of strong baseline system which uses multi-lingual training and back-translation. |
From Research to Production and Back: Ludicrously Fast Neural Machine Translation (D19-56)
Copied to clipboard
Young Jin Kim, Marcin Junczys-Dowmunt, Hany Hassan, Alham Fikri Aji, Kenneth Heafield, Roman Grundkiewicz, Nikolay Bogoychev
| Challenge: | Using the dominating submissions to the previous edition of the shared task, we develop improved teacher-student training via multi-agent dual-learning and noisy backward-forward translation for Transformer-based student models. |
| Approach: | They propose to use multi-agent dual-learning and noisy backward-forward translation to improve teacher-student training for Transformer-based student models. |
| Outcome: | The proposed model outperforms submissions to the previous edition of the WNGT efficiency shared task by 4 BLEU points and 10 BLUE points respectively. |
Document Flattening: Beyond Concatenating Context for Document-Level Neural Machine Translation (2023.eacl-main)
Copied to clipboard
| Challenge: | Existing document-level neural machine translation systems concatenate several consecutive sentences to form a pseudo-document, and then learn inter-sentential dependencies. |
| Approach: | They propose a document flattening technique that integrates Flat-Batch Attention (FBA) and Neural Context Gate (NCG) into Transformer model to utilize information beyond the pseudo-document boundaries. |
| Outcome: | The proposed method outperforms baselines on BLEU, COMET and accuracy on the contrastive test set. |
Efficiency through Auto-Sizing: Notre Dame NLP’s Submission to the WNGT 2019 Efficiency Task (D19-56)
Copied to clipboard
| Challenge: | Notre Dame Natural Language Processing group applied auto-sizing to the Transformer network to reduce the number of parameters in the model. |
| Approach: | They investigated the impact of auto-sizing on the Transformer network by applying a method to inducing sparsity in parameters. |
| Outcome: | The proposed method eliminated more than 25% of the model’s parameters while suffering a decrease of only 1.1 BLEU. |
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. |
Text Generation from Discourse Representation Structures (2021.naacl-main)
Copied to clipboard
| Challenge: | Existing models to generate text from formal meaning representations based on Discourse Representation Structures (DRSs) . |
| Approach: | They propose neural models to generate text from formal meaning representations based on Discourse Representation Structures (DRSs). |
| Outcome: | The proposed model achieves competitive performance on the GMB benchmark against several strong baselines. |
A Stable and Effective Learning Strategy for Trainable Greedy Decoding (D18-1)
Copied to clipboard
| Challenge: | Existing methods for decoding text using beam search are expensive and require reinforcement learning. |
| Approach: | They propose a method that allows us to reap the full benefits of beam search with no additional computational cost. |
| Outcome: | The proposed method outperforms greedy decoding and beam search on machine translation tasks with minimal computational cost. |
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). |
MobileNMT: Enabling Translation in 15MB and 30ms (2023.acl-industry)
Copied to clipboard
| Challenge: | Existing work on NMT models is limited in storage, memory, computation and power consumption. |
| Approach: | They propose a mobile machine translation system that can translate in 15MB and 30ms on devices. |
| Outcome: | The proposed system can translate in 15MB and 30ms on mobile devices. |
Filtering and Mining Parallel Data in a Joint Multilingual Space (P18-2)
Copied to clipboard
| Challenge: | Using a cosine distance in a joint multilingual sentence embedding, we filter out noisy parallel data and mine for bitexts in large news collections. |
| Approach: | They propose to learn a joint multilingual sentence embedding and use the distance between sentences in different languages to filter noisy parallel data and to mine for parallel data in large monolingual texts. |
| Outcome: | The proposed approach improves a competitive baseline on the WMT'14 task by 0.3 BLEU by filtering out 25% of the training data. |
Pre-training via Leveraging Assisting Languages for Neural Machine Translation (2020.acl-srw)
Copied to clipboard
| Challenge: | Sequence-to-sequence (S2S) pre-training with large monolingual data is not always available for the languages of interest (LOI). |
| Approach: | They propose to use monolingual corpora of other languages to complement the scarce monolingual LOI by script mapping (Chinese to Japanese) . Using only Chinese and French monolinguals, they improve Japanese-English translation quality by up to 8.5 BLEU in low-resource scenarios. |
| Outcome: | The proposed approach improves Japanese-English translation quality by up to 8.5 BLEU in low-resource scenarios. |
Lipschitz Constrained Parameter Initialization for Deep Transformers (2020.acl-main)
Copied to clipboard
| Challenge: | Existing studies show that deep Transformers have difficulty in training even with residual connection and layer normalization. |
| Approach: | They propose a method that leverages the Lipschitz constraint on the initialization of Transformer parameters to ease the optimization difficulties caused by its multi-layer encoder/decoder structure. |
| Outcome: | The proposed model outperforms previous RNN/CNN models but fails to converge with the original computation order. |
RadEval: A framework for radiology text evaluation (2025.emnlp-demos)
Copied to clipboard
Justin Xu, Xi Zhang, Javid Abderezaei, Julie Bauml, Roger Boodoo, Fatemeh Haghighi, Ali Ganjizadeh, Eric Brattain, Dave Van Veen, Zaiqiao Meng, David W Eyre, Jean-Benoit Delbrouck
| Challenge: | Evaluating automated radiology report generation systems remains a fundamental challenge in the development of safe, accurate, and clinically useful medical AI. |
| Approach: | They propose a unified, open-source framework for evaluating radiology texts that consolidates a diverse range of metrics from classic ngram overlap (BLEU) and contextual measures (BERTScore) to clinical concept-based scores (GREEN). |
| Outcome: | The framework consolidates a diverse range of metrics from ngram overlap (BLEU) and contextual measures (BERTScore) to clinical concept-based scores (F1CheXbert, F1RadGraph, RaTEScore, SRR-BERT, TemporalEntityF1) and advanced LLMbased evaluators (GREEN). |
Opportunistic Decoding with Timely Correction for Simultaneous Translation (2020.acl-main)
Copied to clipboard
| Challenge: | Existing approaches to balancing translation quality and latency are either too aggressive or too conservative. |
| Approach: | They propose an opportunistic decoding technique that always (over-)generates a certain mount of extra words at each step to keep the audience on track with the latest information. |
| Outcome: | The proposed technique reduces latency and increases BLEU with no over-generating . it also corrects mistakes in the overgenerated words when observing more context . |
VizSeq: a visual analysis toolkit for text generation tasks (D19-3)
Copied to clipboard
| Challenge: | Several softwares for text evaluation are available that do not provide detailed examples. |
| Approach: | They propose a visual analysis toolkit for instance-level and corpus-level system evaluation on a wide variety of text generation tasks. |
| Outcome: | The proposed toolkit covers most common n-gram metrics and latest embedding-based metrics such as BERTScore. |
Bi-Directional Differentiable Input Reconstruction for Low-Resource Neural Machine Translation (N19-1)
Copied to clipboard
| Challenge: | Existing work has addressed this problem by leveraging monolingual or multilingual data. |
| Approach: | They propose to introduce a differentiable reconstruction loss for neural machine translation to exploit the limited amounts of parallel text available in low-resource settings. |
| Outcome: | The proposed approach achieves small but consistent BLEU improvements on four language pairs in both translation directions and outperforms an alternative differentiable reconstruction strategy based on hidden states. |
ChrEn: Cherokee-English Machine Translation for Endangered Language Revitalization (2020.emnlp-main)
Copied to clipboard
| Challenge: | Cherokee is a highly endangered Native American language spoken by the Cherokee people . there are only 2,000 fluent first language Cherokee speakers remaining in the world . |
| Approach: | They propose a Cherokee-English parallel dataset to facilitate machine translation between Cherokee and English. |
| Outcome: | The proposed dataset compares Cherokee-English and English-Cherokee machine translation systems . the results show that the datasets are low-resource and low-cost compared to other datasets . |
Understanding Back-Translation at Scale (D18-1)
Copied to clipboard
| Challenge: | An effective method to improve neural machine translation with monolingual data is to augment the parallel training corpus with back-translations of target language sentences. |
| Approach: | They propose to augment parallel training corpus with back-translations of target language sentences to improve neural machine translation with monolingual data. |
| Outcome: | The proposed method achieves a state-of-the-art of 35 BLEU on the WMT’14 English-German test set. |
Adaptive Multi-pass Decoder for Neural Machine Translation (D18-1)
Copied to clipboard
| Challenge: | End-to-end neural machine translation (NMT) has attracted increasing attention in recent years. |
| Approach: | They propose an adaptive multi-pass decoder which introduces a flexible multi- pass polishing mechanism to extend the capacity of NMT via reinforcement learning. |
| Outcome: | The proposed architecture improves Chinese-English translation with 1.55 BLEU . the proposed architecture adopts a flexible multi-pass polishing mechanism . |
Extracting Latent Steering Vectors from Pretrained Language Models (2022.findings-acl)
Copied to clipboard
| Challenge: | Prior work on controllable text generation has focused on learning how to control language models through trainable decoding, smart-prompt design, or fine-tuning based on a desired objective. |
| Approach: | They propose to extract latent vectors directly from pretrained language model decoders without fine-tuning. |
| Outcome: | The proposed approach generates a target sentence nearly perfectly for English sentences . it outperforms pooled hidden states of models on a textual similarity benchmark . |
On Orthogonality Constraints for Transformers (2021.acl-short)
Copied to clipboard
Aston Zhang, Alvin Chan, Yi Tay, Jie Fu, Shuohang Wang, Shuai Zhang, Huajie Shao, Shuochao Yao, Roy Ka-Wei Lee
| Challenge: | a dedicated study on orthogonality constraints for transformers has been lacking . plug-and-play constraints increase the BLEU of transformers . |
| Approach: | They propose to use plug-and-play constraints to encourage matrices to be orthogonal for numerical stability. |
| Outcome: | The proposed constraint increases the BLEU on the large-scale WMT’16 EnDe benchmark by a factor of 28.4 to 29.6. |
Learning When to Translate for Streaming Speech (2022.acl-long)
Copied to clipboard
| Challenge: | Existing methods waiting-and-translating for a fixed duration break speech acoustic units . Existing models waiting-for a set duration and generating partial sentences are not effective . |
| Approach: | They propose a monotonic segmentation module inside an encoder-decoder model to detect proper speech unit boundaries for a streaming speech input. |
| Outcome: | The proposed method outperforms existing methods on a speech translation dataset and achieves the best trade-off between translation quality and latency. |
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. |
A Comparison of Transformer and Recurrent Neural Networks on Multilingual Neural Machine Translation (C18-1)
Copied to clipboard
| Challenge: | Recent studies have shown that multilingual NMT models can handle more than one translation direction with a single system. |
| Approach: | They propose a multilingual neural machine translation model that can handle more than one translation direction with a single system. |
| Outcome: | The proposed model performs well in low-resource settings against bilingual systems. |
Evaluating Dialogue Generation Systems via Response Selection (2020.acl-main)
Copied to clipboard
| Challenge: | Existing automatic evaluation metrics for open-domain dialogue systems correlate poorly with human evaluation. |
| Approach: | They propose to construct response selection test sets with well-chosen false candidates to evaluate response generation systems via response selection. |
| Outcome: | The proposed method correlates with human evaluation better than widely used metrics such as BLEU. |
Revisiting Evaluation of Question Answering Systems in Low-Resource Indic Languages: Bridging Human and Metric Alignment (2026.acl-short)
Copied to clipboard
| Challenge: | Evaluating Question Answering systems in low-resource Indic languages remains challenging due to the scarcity of annotated data and the lack of reliable evaluation metrics. |
| Approach: | They propose a language-based multi-aspect evaluation framework for question answering systems . the framework integrates semantic similarity, factual completeness, numerical accuracy and contextual relevance . |
| Outcome: | The proposed metric is evaluated across eight Indic-language QA tasks using multiple LLMs . Across all settings, it shows stronger agreement with human evaluation . |
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. |
Does the Order of Training Samples Matter? Improving Neural Data-to-Text Generation with Curriculum Learning (2021.eacl-main)
Copied to clipboard
| Challenge: | Recent advances in data-to-text generation have been focused on curriculum learning, which is a process of presenting training data in a specific order, starting from easy examples and moving on to more difficult ones, as the learner becomes more competent. |
| Approach: | They propose to use a curriculum learning process to change the order of training samples in a model based on the model's competence to improve model performance and convergence speed. |
| Outcome: | The proposed model shows faster convergence speed and reduced training time by 38.7% and performance by 4.84 BLEU. |
InstructPTS: Instruction-Tuning LLMs for Product Title Summarization (2023.emnlp-industry)
Copied to clipboard
| Challenge: | E-commerce product catalogs contain billions of items with lengthy titles . this leads to a gap between how customers refer to these unnatural titles - and how they are used . |
| Approach: | They propose a novel approach to product title summarization that uses a fine-tuned instruction strategy to train a highly accurate model. |
| Outcome: | The proposed approach can generate more accurate product title summaries with an improvement of over 14 and 8 BLEU and ROUGE points. |
Textless Speech-to-Speech Translation on Real Data (2022.naacl-main)
Copied to clipboard
Ann Lee, Hongyu Gong, Paul-Ambroise Duquenne, Holger Schwenk, Peng-Jen Chen, Changhan Wang, Sravya Popuri, Yossi Adi, Juan Pino, Jiatao Gu, Wei-Ning Hsu
| Challenge: | Existing text-based speech-to-speech translation systems rely on cascaded approach . text-to text translation systems require text generation and a single input to generate output . |
| Approach: | They propose a textless speech-to-speech translation system that can translate speech from one language into another without the need of text data. |
| Outcome: | The proposed system can translate speech from one language into another without text data. |
Surprisingly Easy Hard-Attention for Sequence to Sequence Learning (D18-1)
Copied to clipboard
| Challenge: | Existing attention mechanisms are hard and hard, but they are more accurate when trained. |
| Approach: | They propose to use a beam approximation of the joint distribution between attention and output to train sequence to sequence learning. |
| Outcome: | The proposed method is compared to existing attention mechanisms on five translation tasks and shows consistent gains on the same tasks. |
Multilingual Speech Translation from Efficient Finetuning of Pretrained Models (2021.acl-long)
Copied to clipboard
Xian Li, Changhan Wang, Yun Tang, Chau Tran, Yuqing Tang, Juan Pino, Alexei Baevski, Alexis Conneau, Michael Auli
| Challenge: | Recent advances in text pretraining and finetuning have improved multitasking applications significantly. |
| Approach: | They propose a minimalistic LNA finetuning approach to build multilingual speech-to-text translation using a pretrained speech encoder and text decoder. |
| Outcome: | The proposed approach surpasses the cascaded ST benchmark for 36 translation directions on the large-scale multilingual ST benchmark CoVoST 2. |
NLG Evaluation Metrics Beyond Correlation Analysis: An Empirical Metric Preference Checklist (2023.acl-long)
Copied to clipboard
| Challenge: | a systematic review of automatic evaluation metrics for Natural Language Generation (NLG) shows that task-agnostic metrics have a weak correlation with human . |
| Approach: | They propose a framework to assess the effectiveness of automatic metrics in three NLG tasks . they propose task-agnostic and human-aligned metrics to be used for evaluation . |
| Outcome: | The proposed framework provides access to the evaluation tools for three NLG tasks. |
Iterative Refinement in the Continuous Space for Non-Autoregressive Neural Machine Translation (2020.emnlp-main)
Copied to clipboard
| Challenge: | Existing non-autoregressive inference procedures that refine in token space often require computational overhead. |
| Approach: | They propose an efficient inference procedure that iteratively refines translation purely in the continuous space using a latent variable instead of the latent variables. |
| Outcome: | The proposed procedure is twice as efficient and more effective than the existing EM-like inference procedure. |
Self-Attention with Relative Position Representations (N18-2)
Copied to clipboard
| Challenge: | Recent approaches to sequence to sequence learning leverage recurrence, convolution, attention or combination of recurrent and convolutional neural networks. |
| Approach: | They propose an approach that extends the self-attention mechanism to consider representations of relative positions, or distances between sequence elements. |
| Outcome: | The proposed approach yields 1.3 BLEU and 0.3 BLUE on translation tasks . it is based on a relation-aware self-attention mechanism that can generalize to arbitrary graph-labeled inputs. |
Investigating Text Simplification Evaluation (2021.findings-acl)
Copied to clipboard
| Challenge: | Existing studies show that parallel TS corpora contain inaccurate simplifications and incorrect alignments. |
| Approach: | They propose to improve the distribution of parallel text simplification corpora to build more robust TS models. |
| Outcome: | The proposed models can be improved by improving the distribution of TS datasets. |
Incremental Decoding and Training Methods for Simultaneous Translation in Neural Machine Translation (N18-2)
Copied to clipboard
| Challenge: | a tunable agent decides the best segmentation strategy for a user-defined BLEU loss and Average Proportion (AP) constraint. |
| Approach: | They propose a tunable agent which decides the best segmentation strategy for a user-defined BLEU loss and average proportion (AP) constraint. |
| Outcome: | The proposed agent outperforms existing Wait-if-diff and Wait-If-worse agents on BLEU with a lower latency. |
Analysis on Unsupervised Acquisition Process of Bilingual Vocabulary through Iterative Back-Translation (2024.lrec-main)
Copied to clipboard
| Challenge: | Existing studies have demonstrated the effectiveness of iterative back-translation, but its reason has not been sufficiently elucidated. |
| Approach: | They propose a method for machine translation known as iterative back-translation . they use two monolingual data to create a pseudo-bilingual data and update translation models . |
| Outcome: | The proposed method improves translation quality and improves BLEU. |
Pivot-based Transfer Learning for Neural Machine Translation between Non-English Languages (D19-1)
Copied to clipboard
| Challenge: | Using parallel corpora, we train a single, direct NMT model for non-English language pairs. |
| Approach: | They propose three ways to increase the relation among source, pivot, and target languages in pre-training . they use additional adapter component to smoothly connect pre-trained encoder and decoder . |
| Outcome: | The proposed methods outperform multilingual models up to +2.6% BLEU in WMT 2019 French-German and German-Czech tasks. |
Rewarding Semantic Similarity under Optimized Alignments for AMR-to-Text Generation (2022.acl-short)
Copied to clipboard
| Challenge: | Automatic evaluation metrics score natural language generation systems based on how well they lexically align to humanannotated references. |
| Approach: | They propose to replace greedy alignments in BERTScore with optimized ones that replace the n-gram matching BERTAcore metrics with a token embedding to prevent domain mismatch. |
| Outcome: | The proposed metrics outperform cross-entropy and BLEU reward baselines on AMR-to-text generation. |
Cost-Effective E-Commerce Catalog Translation at Scale Ensuring Named Entity Protection (2025.emnlp-industry)
Copied to clipboard
Asier Gutiérrez-Fandiño, Jorge Yero Salazar, Clement Ruin, Alejandro Quintero-Roba, Shangeetha Ravichandran, Jesus Perez-Martin, Pankaj Adsul, Suruchi Garg, Leonardo Lezcano
| Challenge: | a new translation platform for global e-commerce is delivering high quality, contextually accurate multilingual content. |
| Approach: | They propose a translation platform for global e-commerce that combines daily batch and real-time API pipelines with optimized T5-based models and a Reference Generator to enforce >99% non-translatable entity preservation. |
| Outcome: | The proposed translation platform achieves 10–100 cost savings over general-purpose LLMs for EnglishSpanish and EnglishFrench translation. |
Long-Short Term Masking Transformer: A Simple but Effective Baseline for Document-level Neural Machine Translation (2020.emnlp-main)
Copied to clipboard
| Challenge: | Recent advances in deep learning have led to significant improvement of document-level neural machine translation (NMT). |
| Approach: | They propose a long-short term masking self-attention on top of the standard transformer to capture the long-range dependence and reduce the propagation of errors. |
| Outcome: | The proposed model captures the long-range dependence and reduces errors on two publicly available document-level datasets. |
A Study in Improving BLEU Reference Coverage with Diverse Automatic Paraphrasing (2020.findings-emnlp)
Copied to clipboard
| Challenge: | Using neural paraphrasing techniques, we investigate whether automatically generating additional *diverse* references can provide better coverage of the space of valid translations. |
| Approach: | They propose to use neural paraphrasing techniques to generate additional references that provide better coverage of the space of valid translations. |
| Outcome: | The proposed approach beats human paraphrases in the BLEU evaluation. |
Improving Deep Transformer with Depth-Scaled Initialization and Merged Attention (D19-1)
Copied to clipboard
| Challenge: | Existing methods to improve NLP convergence and computational overhead are limited by stacking more layers. |
| Approach: | They propose a depth-scaled initialization method which reduces parameter variance at initialization and reduces output variance of residual connections to ease gradient back-propagation. |
| Outcome: | The proposed method outperforms the base model on translation tasks with five translation directions while matching the decoding speed of the baseline model. |
Non-Autoregressive Machine Translation with Latent Alignments (2020.emnlp-main)
Copied to clipboard
| Challenge: | Existing non-autoregressive machine translation methods are lacking in the field of latent alignments. |
| Approach: | They propose two strong methods for non-autoregressive machine translation that model latent alignments with dynamic programming. |
| Outcome: | The proposed models achieve state-of-the-art on the WMT’14 EnDe task, compared with the autoregressive Transformer baseline. |
Training for Diversity in Image Paragraph Captioning (D18-1)
Copied to clipboard
| Challenge: | Existing image captioning models have a lack of diversity between sentences . current models have limited their effectiveness due to repetitive paragraphs . |
| Approach: | They propose to apply sequence-level training to image paragraph captioning models . they find that standard self-critical training produces poor results . |
| Outcome: | The proposed training improves on the Visual Genome dataset with no architectural changes. |
Analyzing the Performance of Large Language Models on Code Summarization (2024.lrec-main)
Copied to clipboard
| Challenge: | Large language models perform very well on tasks that involve both natural language and source code. |
| Approach: | They show that large language models perform very well on tasks that involve both natural language and source code. |
| Outcome: | The proposed models perform very well on tasks that involve both natural language and source code. |
Harnessing Multilinguality in Unsupervised Machine Translation for Rare Languages (2021.naacl-main)
Copied to clipboard
| Challenge: | Unsupervised translation systems have impressive performance on resource-rich language pairs . however, in more realistic settings, unsupervised systems perform poorly . |
| Approach: | They propose a model for 5 low-resource languages that leverages monolingual and auxiliary parallel data from other high-resourced languages. |
| Outcome: | The proposed model outperforms state-of-the-art models on low-resource languages . it also matches the current state- of-the art model for Nepali-English . |
Assessing Reference-Free Peer Evaluation for Machine Translation (2021.naacl-main)
Copied to clipboard
| Challenge: | Existing methods to evaluate machine translation output are based on comparing MT output to one or more reference translations. |
| Approach: | They propose to use probabilities given by a large, multilingual model as a reference-free metric. |
| Outcome: | The proposed model is robust and likely to offer reasonable performance across a broad spectrum of domains and different system qualities. |
The Inside Story: Towards Better Understanding of Machine Translation Neural Evaluation Metrics (2023.acl-short)
Copied to clipboard
| Challenge: | Neural metrics for machine translation evaluation are considered "black boxes" lexical overlap-based metrics are popular for evaluation of translation systems and algorithms . |
| Approach: | They develop and compare several neural explainability methods to understand translation errors . they aim to better understand the correspondence between token-level explanations and human annotated error spans . |
| Outcome: | The proposed methods leverage token-level information that can be directly attributed to translation errors. |
AugNLG: Few-shot Natural Language Generation using Self-trained Data Augmentation (2021.acl-long)
Copied to clipboard
| Challenge: | Large-scale conversational systems typically generate unnatural, robotic responses using template-based approaches. |
| Approach: | They propose a data augmentation approach that combines a self-trained neural retrieval model with a few-shot learned NLU model to automatically create MR-to-Text data from open-domain texts. |
| Outcome: | The proposed approach outperforms the state-of-the-art methods on the FewshotWOZ data in both BLEU and Slot Error Rate. |
The Multilingual Microblog Translation Corpus: Improving and Evaluating Translation of User-Generated Text (2022.lrec-1)
Copied to clipboard
| Challenge: | a corpus of over 200,000 microblog translations supports translation of thirteen languages into English . large collections of parallel text, or bitext, are increasingly available in many languages . |
| Approach: | They propose a corpus of over 200,000 microblog posts that supports translation of thirteen languages into English. |
| Outcome: | The proposed corpus contains over 200,000 translations of microblog posts in 13 languages . fine-tuning showed significant improvements in translation quality . |
Condensing Multilingual Knowledge with Lightweight Language-Specific Modules (2023.emnlp-main)
Copied to clipboard
| Challenge: | Existing methods to boost performance in multilingual models but scalability is difficult to manage. |
| Approach: | They propose a method that incorporates language-specific (LS) modules to boost model performance. |
| Outcome: | The proposed method outperforms state-of-the-art methods while outperforming existing methods. |
A Mixed Hierarchical Attention Based Encoder-Decoder Approach for Standard Table Summarization (N18-2)
Copied to clipboard
| Challenge: | Structured data summarization involves generation of summaries from structured input data. |
| Approach: | They propose a hierarchical attention-based encoder-decoder model which leverages the structure in addition to the content of the tables. |
| Outcome: | The proposed model improves on the weathergov dataset by 30% over the current state-of-the-art. |
SwitchOut: an Efficient Data Augmentation Algorithm for Neural Machine Translation (D18-1)
Copied to clipboard
| Challenge: | Existing methods for data augmentation for text-based tasks such as machine translation are limited due to noise and noise. |
| Approach: | They propose a data augmentation policy with desirable properties as an optimization problem and propose 'SwitchOut' switchout randomly replaces words in both the source and target sentences with other random words from their corresponding vocabularies. |
| Outcome: | The proposed method outperforms strong alternatives such as word dropout on three translation datasets. |
White-Box Multi-Objective Adversarial Attack on Dialogue Generation (2023.acl-long)
Copied to clipboard
| Challenge: | Pre-trained transformers are popular in state-of-the-art dialogue generation systems . however, they are vulnerable to adversarial samples crafted by small and imperceptible perturbations. |
| Approach: | They propose a multi-objective attack method that balances two objectives: generation accuracy and length. |
| Outcome: | The proposed method significantly degrades state-of-the-art DG models with a higher success rate than traditional accuracy-based methods. |
Learn To Remember: Transformer with Recurrent Memory for Document-Level Machine Translation (2022.findings-naacl)
Copied to clipboard
| Challenge: | Recent studies have shown that the effective use of contextual information between sentences can achieve better performance in document-level machine translation. |
| Approach: | They propose a recurrent memory unit to the Transformer to support the information exchange between the sentence and previous context. |
| Outcome: | The proposed model outperforms the previous work on TED and News by 0.91 s-BLEU and 1.49 d-BLUE on average. |
Navigating the Metrics Maze: Reconciling Score Magnitudes and Accuracies (2024.acl-long)
Copied to clipboard
| Challenge: | a decade ago a single metric, BLEU, governed progress in machine translation research. |
| Approach: | They investigate the "dynamic range" of a number of modern machine translation metrics to provide a collective understanding of differences in scores . they use a large dataset to discover deltas at which metrics achieve system-level differences that are meaningful to humans . |
| Outcome: | The proposed method is more stable than statistical p-values in regards to testset size. |
Retrieval-Based Neural Code Generation (D18-1)
Copied to clipboard
Shirley Anugrah Hayati, Raphael Olivier, Pravalika Avvaru, Pengcheng Yin, Anthony Tomasic, Graham Neubig
| Challenge: | Existing methods to generate program source code from natural language are not able to generate complex code due to a lack of ability to memorize large and complex structures. |
| Approach: | They propose a method that uses subtree retrieval to explicitly reference existing code examples within a neural code generation model. |
| Outcome: | The proposed method improves performance on two code generation tasks by up to +2.6 BLEU. |
Learning Simplifications for Specific Target Audiences (P18-2)
Copied to clipboard
| Challenge: | Text simplification is a monolingual text-to-text transformation task . data from TS data can contain multiple simplifications of the same original text . |
| Approach: | They propose to use sequence-to-sequence neural models to build models tailored for specific grade levels. |
| Outcome: | The proposed model outperforms state-of-the-art approaches for a monolingual text-to-text transformation task. |
Multi-perspective Preference Alignment of LLMs for Programming-Community Question Answering (2025.coling-main)
Copied to clipboard
| Challenge: | Extensive experiments on a high-quality, real-world PCQA dataset validate its accuracy and preference. |
| Approach: | They propose a multi-perspective preference alignment for programming-community question answering to generate user-centric responses. |
| Outcome: | Experiments on a high-quality, real-world PCQA dataset validate the proposed model's accuracy and preference. |
Split and Rephrase: Better Evaluation and Stronger Baselines (P18-2)
Copied to clipboard
| Challenge: | a dataset mapping a complex sentence to a sequence of sentences conveying the same meaning is challenging in NLP. |
| Approach: | They propose a neural split and a copy-mechanism to break a complex sentence into several shorter sentences that convey the same meaning. |
| Outcome: | The proposed model outperforms the baseline model by 8.68 BLEU and further improves on the task. |
When a Good Translation is Wrong in Context: Context-Aware Machine Translation Improves on Deixis, Ellipsis, and Lexical Cohesion (P19-1)
Copied to clipboard
| Challenge: | et al., 2018: translation errors due to the lack of extra-sentential context are becoming more and more noticeable among otherwise adequate translations. |
| Approach: | They propose a context-aware translation model that uses sentence-level data to identify inconsistencies . standard metrics are not sensitive to improvements in consistency in document-level translations . |
| Outcome: | The proposed model shows major gains over baseline without sacrificing performance . standard metrics are not sensitive to improvements in document-level translations . |
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). |
Document Context Neural Machine Translation with Memory Networks (P18-1)
Copied to clipboard
| Challenge: | Experimental results show that our model exploits both source and target document context. |
| Approach: | They propose a document-level neural machine translation model which takes both source and target document context into account using memory networks. |
| Outcome: | The proposed model outperforms previous work in terms of BLEU and METEOR in English translations. |
Competence-based Curriculum Learning for Neural Machine Translation (N19-1)
Copied to clipboard
| Challenge: | Existing NMT systems require specialized heuristics and large batch sizes. |
| Approach: | They propose a curriculum learning framework for NMT that reduces training time and costs . framework consists of a principled way of deciding which training samples are shown to the model . |
| Outcome: | The proposed framework can reduce training time and improve performance of recurrent neural network models and Transformers. |
Effective Cross-lingual Transfer of Neural Machine Translation Models without Shared Vocabularies (P19-1)
Copied to clipboard
| Challenge: | Existing approaches to transfer a pretrained NMT model to a new, unrelated language without shared vocabularies are limited to cognate languages. |
| Approach: | They propose to transfer a pretrained NMT model to a new, unrelated language without shared vocabularies by using cross-lingual word embedding and injecting artificial noises. |
| Outcome: | The proposed methods outperform multilingual joint training by a large margin in five low-resource 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. |
“Wikily” Supervised Neural Translation Tailored to Cross-Lingual Tasks (2021.emnlp-main)
Copied to clipboard
| Challenge: | Unsupervised neural machine translation models perform well in low-resource or distant languages. |
| Approach: | They propose a model that leverages Wikipedia for machine translation and cross-lingual tasks without supervision from external parallel data or supervised models in target language. |
| Outcome: | The proposed model outperforms supervised models in Arabic and English translation tasks. |
Machine Translation between Spoken Languages and Signed Languages Represented in SignWriting (2023.findings-eacl)
Copied to clipboard
| Challenge: | Yin et al. ( 2021) calls for including sign language processing (SLP) in natural language processing research. |
| Approach: | They propose to use a sign language writing system to parse, factorize, decode and evaluate signed languages. |
| Outcome: | The proposed method achieves over 30 BLEU in a bilingual setup and over 20 BLUE in two multilingual setups. |
Speechformer: Reducing Information Loss in Direct Speech Translation (2021.emnlp-main)
Copied to clipboard
| Challenge: | Current approaches to speech-to-text translation (ST) use a pipeline of two sub-components - an automatic speech recognition (ASR) and a machine translation (MT) model. |
| Approach: | They propose an architecture that avoids initial lossy compression and aggregates information only at a higher level according to more informed linguistic criteria. |
| Outcome: | The proposed architecture achieves gains of up to 0.8 BLEU on the standard MuST-C corpus and up to 4.0 BLUE in a low resource scenario. |
DETECT: Determining Ease and Textual Clarity of German Text Simplifications (2026.eacl-long)
Copied to clipboard
| Challenge: | Current evaluation of German automatic text simplification relies on general-purpose metrics such as SARI, BLEU, and BERTScore. |
| Approach: | They propose a German-specific metric that holistically evaluates ATS quality across all three dimensions of simplicity, meaning preservation, and fluency. |
| Outcome: | The proposed metric achieves higher correlations with human judgments than widely used ATS metrics. |
Beyond Pointwise Scores: Decomposed Criteria-Based Evaluation of LLM Responses (2025.emnlp-industry)
Copied to clipboard
| Challenge: | DeCE is model-agnostic and domain-general, requiring no predefined taxonomies or handcrafted rubrics. |
| Approach: | They propose a decomposed LLM evaluation framework that separates accuracy and recall from accuracy and relevance. |
| Outcome: | The proposed framework achieves stronger correlation with expert judgments than traditional metrics and pointwise LLM scoring. |
Investigating the Effectiveness of BPE: The Power of Shorter Sequences (D19-1)
Copied to clipboard
| Challenge: | Byte-Pair Encoding (BPE) is an unsupervised sub-word tokenization technique, but its reasons for its effectiveness are not well understood. |
| Approach: | They link BPE to the broader family of dictionary-based compression algorithms and compare it with other members of this family. |
| Outcome: | The proposed method is compared with dictionary-based compression algorithms and improves on a fixed vocabulary size budget. |
AssameseBackTranslit: Back Transliteration of Romanized Assamese Social Media Text (2024.lrec-main)
Copied to clipboard
| Challenge: | a novel dataset capturing native text composed in the Roman/Latin script is presented . the dataset comprises 60,312 Roman-native parallel transliterated sentences . |
| Approach: | They propose a back transliteration dataset capturing native text composed in the Roman/Latin script and its corresponding representation in the native Assamese script. |
| Outcome: | The proposed dataset outperforms baseline models in terms of word-level transliteration evaluation benchmarks and performance assessments. |
ICE-Score: Instructing Large Language Models to Evaluate Code (2024.findings-eacl)
Copied to clipboard
| Challenge: | Recent advances in the field of natural language generation have facilitated the use of large language models to assess the quality of generated text. |
| Approach: | They propose a new evaluation metric by instructing large language models for code assessments using a set of programming languages. |
| Outcome: | The proposed evaluation metric surpasses state-of-the-art metrics for code generation, delivering high levels of accuracy and consistency across programming languages and tasks. |
Bitext Mining Using Distilled Sentence Representations for Low-Resource Languages (2022.findings-emnlp)
Copied to clipboard
| Challenge: | a new study aims to extend multilingual representation learning beyond the hundred most frequent languages . current work on multilingual sentence representations has focused on training one model which handles all languages of interest . |
| Approach: | They propose a teacher-student approach to extend existing monolingual sentence embedding space to new languages. |
| Outcome: | The proposed model outperforms the original LASER encoder in 44 African languages . the model can be used to train multiple languages and learn new languages if they have the same training data . |
How Reliable are Model Diagnostics? (2021.findings-acl)
Copied to clipboard
| Challenge: | Contemporary statistical models trade off interpretability and simplicity for powerful parameterizations and inductive biases, enabling impressive performance. |
| Approach: | They examine three recent models and find they are not yet reliable . they also formulate recommendations for practitioners and researchers . |
| Outcome: | The proposed models are not as reliable as previously assumed, the authors argue . their findings suggest that they are needed for improving models and training setups . |
On Systematic Style Differences between Unsupervised and Supervised MT and an Application for High-Resource Machine Translation (2022.naacl-main)
Copied to clipboard
| Challenge: | Modern unsupervised machine translation systems reach reasonable translation quality under clean and controlled data conditions. |
| Approach: | They compare unsupervised and supervised machine translation systems of similar quality . they combine the benefits of both methods into a single system . |
| Outcome: | The proposed system improves adequacy and fluency as measured by human evaluators. |
Weight Distillation: Transferring the Knowledge in Neural Network Parameters (2021.acl-long)
Copied to clipboard
| Challenge: | Knowledge distillation is an effective method for model acceleration and compression. |
| Approach: | They propose to use parameters to distill knowledge from large neural networks to small ones . they propose to do this by using a parameter generator to transfer the knowledge to a small neural network . |
| Outcome: | The proposed method learns a small network 1.88 2.94x faster than the large network but with competitive BLEU points. |
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. |
Reliability and Learnability of Human Bandit Feedback for Sequence-to-Sequence Reinforcement Learning (P18-1)
Copied to clipboard
| Challenge: | Recent work has shown that reinforcement learning (RL) can be scaled to games with large state-action spaces, achieving human-level performance or even superhuman performance. |
| Approach: | They propose to use bandit feedback to improve sequence-to-sequence learning by simulating reward signals by evaluation metrics such as BLEU, F1-score, or ROUGE. |
| Outcome: | The proposed methods improve performance even from small amounts of human feedback, pointing to a great potential for applications at larger scale. |
GRAFT: A Graph-based Flow-aware Agentic Framework for Document-level Machine Translation (2025.emnlp-industry)
Copied to clipboard
| Challenge: | Existing Document-level machine translation systems struggle to handle discourse-level phenomena such as pronoun resolution, lexical cohesion, and ellipsis. |
| Approach: | They propose a graph-based document-level machine translation framework that leverages Large Language Models to model translation flow and discourse structure. |
| Outcome: | The proposed framework outperforms commercial and closed systems in eight languages and six domains. |
Accuracy is not enough: Evaluating Personalization in Summarizers (2023.findings-emnlp)
Copied to clipboard
| Challenge: | Existing accuracy measures cannot evaluate the degree of personalization of summarization models. |
| Approach: | They propose to use a PENS dataset to analyze the degree of personalization of ten different summarization models. |
| Outcome: | The proposed measure can evaluate the degree of personalization of summarization models using the PENS dataset. |
If beam search is the answer, what was the question? (2020.emnlp-main)
Copied to clipboard
| Challenge: | surprisingly, beam search results on language generation tasks are low-quality . despite its high error rate, beam searches can be used to decode models with high probability . |
| Approach: | They frame beam search as the exact solution to a different decoding objective . they propose a set of decoding objectives that explicitly enforce this property . |
| Outcome: | The proposed method enforces uniform information density in text, a property motivated by cognitive science. |
PRINCE: Prefix-Masked Decoding for Knowledge Enhanced Sequence-to-Sequence Pre-Training (2022.emnlp-main)
Copied to clipboard
| Challenge: | Existing studies focus on injecting noises into the input sequence, but feasibility of injecting them into the decoding sequence remains an open question. |
| Approach: | They propose a pre-training paradigm that integrates knowledge-enhanced decoding with noises in the prefix to strengthen the representation learning of entities that span over multiple input tokens. |
| Outcome: | The proposed model achieves state-of-the-art results on two knowledge-driven data-to-text generation tasks with up to 2% BLEU gains. |
Pronoun-Targeted Fine-tuning for NMT with Hybrid Losses (2020.emnlp-main)
Copied to clipboard
| Challenge: | Popular machine translation model training uses backtranslation to improve BLEU scores . we use generative-discriminative hybrid losses to fine-tune a trained model . |
| Approach: | They propose a class of conditional generative-discriminative hybrid losses to fine-tune a machine translation model. |
| Outcome: | The proposed model improves on a sentence-level and contextual model without additional data. |
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%. |
Non-Autoregressive Neural Machine Translation: A Call for Clarity (2022.emnlp-main)
Copied to clipboard
| Challenge: | Non-autoregressive translation models require a single forward pass to generate the output sequence instead of iteratively producing each predicted token. |
| Approach: | They propose to use a single forward pass to generate the output sequence instead of iteratively producing each predicted token. |
| Outcome: | The proposed models improve translation quality and speed under third-party testing environments. |
GEAR: A Scalable and Interpretable Evaluation Framework for RAG-Based Car Assistant Systems (2025.emnlp-industry)
Copied to clipboard
Niloufar Beyranvand, Hamidreza Dastmalchi, Aijun An, Heidar Davoudi, Winston Chan, Ron DiCarlantonio
| Challenge: | Large language models (LLMs) increasingly power car assistants, but evaluating response quality remains a challenge. |
| Approach: | They propose a framework that uses large language models as evaluators to compare assistant responses against ground-truth counterparts. |
| Outcome: | The proposed framework compares assistant responses against ground-truth counterparts, assessing coverage, correctness, and other dimensions of answer quality. |
Word Alignment as Preference for Machine Translation (2024.emnlp-main)
Copied to clipboard
| Challenge: | Hallucination and omission are a problem in machine translation because of an LLM's size and low-resource languages. |
| Approach: | They propose to use word alignment as preference to optimize an LLM-based MT model to mitigate hallucination and omission problems. |
| Outcome: | The proposed model is able to mitigate hallucination and omission by using word alignment as preference. |
A Study of Automatic Metrics for the Evaluation of Natural Language Explanations (2021.eacl-main)
Copied to clipboard
| Challenge: | a lack of transparency is a key issue for robotics and AI. |
| Approach: | They propose to map existing automatic evaluation methods for natural language generation onto explanations. |
| Outcome: | The proposed model shows that embedding-based evaluation methods have higher correlations with human ratings than word-overlap metrics. |
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. |
RoViST: Learning Robust Metrics for Visual Storytelling (2022.findings-naacl)
Copied to clipboard
| Challenge: | Visual storytelling is the task of generating a story paragraph that describes a given image sequence. |
| Approach: | They propose 3 evaluation metrics sets that analyze which aspects we would look for in a good story . they compare their correlation with human judgement scores on a sample of machine stories . |
| Outcome: | The proposed evaluation metrics outperform other metrics on human correlation on a sample of machine stories from state-of-the-art models. |
Differentiable Sampling with Flexible Reference Word Order for Neural Machine Translation (N19-1)
Copied to clipboard
| Challenge: | Existing approaches to correct exposure bias in machine translation are inadequate . scheduled sampling assumes that words are aligned at each time step . |
| Approach: | They propose a differentiable sampling algorithm that optimizes the probability that the reference can be aligned with the sampled output. |
| Outcome: | The proposed approach improves BLEU on translation tasks and is simpler to train with no sampling schedule. |
Keep Meeting Summaries on Topic: Abstractive Multi-Modal Meeting Summarization (P19-1)
Copied to clipboard
| Challenge: | Existing models for extractive summarization of meetings are unfocused and lack content coverage. |
| Approach: | They propose a multi-modal hierarchical attention model that prioritizes segmentation and summarization . they propose to use multi-level hierarchies to narrow down the focus into topically-relevant segments . |
| Outcome: | The proposed model outperforms the state-of-the-art with BLEU and ROUGE measures. |
Losing Heads in the Lottery: Pruning Transformer Attention in Neural Machine Translation (2020.emnlp-main)
Copied to clipboard
| Challenge: | Recent research shows that attention heads are not confident in their decisions and can be pruned. |
| Approach: | They apply the lottery ticket hypothesis to prune heads in early training . they find that the pruned model is 1.5 times faster at inference . |
| Outcome: | The proposed method is 1.5 times faster at inference, but at the cost of longer training. |
Phone Features Improve Speech Translation (2020.acl-main)
Copied to clipboard
| Challenge: | End-to-end models for speech translation more tightly couple speech recognition (ASR) and machine translation (MT) compared to cascades, but performance gap remains in low-resource conditions . |
| Approach: | They propose two methods to incorporate phone features into current neural speech translation models. |
| Outcome: | The proposed models outperform existing models and cascades by up to 9 BLEU on low-resource conditions. |
Paraphrase Generation and Evaluation on Colloquial-Style Sentences (2020.lrec-1)
Copied to clipboard
| Challenge: | a new study investigates the quality and novelty of generated paraphrases . paraphrase models can be used for information retrieval and data mining . |
| Approach: | They use state-of-the-art neural machine translation models trained on the Opusparcus corpus to generate paraphrases in six languages. |
| Outcome: | The proposed model outperforms the existing model on human evaluation in five of the six languages. |
ASPIRO: Any-shot Structured Parsing-error-Induced ReprOmpting for Consistent Data-to-Text Generation (2023.findings-emnlp)
Copied to clipboard
| Challenge: | Unlike previous methods, large language models produce entity-agnostic templates instead of copying the given example entities or validating/crafting the templates manually. |
| Approach: | They propose an approach for structured data verbalisation into short template sentences in zero to few-shot settings that prompts Large Language Models to directly produce entity-agnostic templates. |
| Outcome: | The proposed approach averages 66% parsing error rate reduction in generated verbalisations of RDF triples on the DART dataset. |
Adaptive Feature Selection for End-to-End Speech Translation (2020.findings-emnlp)
Copied to clipboard
| Challenge: | End-to-end speech translation (E2E) models that directly maps audio to a foreign text are not efficient. |
| Approach: | They propose adaptive feature selection (AFS) for encoder-decoder based E2E ST. |
| Outcome: | The proposed model outperforms the existing model on LibriSpeech En-Fr and MuST-C with a BLEU score of 18.56. |
From Heart to Words: Generating Empathetic Responses via Integrated Figurative Language and Semantic Context Signals (2025.findings-acl)
Copied to clipboard
| Challenge: | Existing research on empathy generation focuses on understanding the emotions of the speaker rather than on how the responder conveys empathy. |
| Approach: | They propose to use figurative language and causal semantic context to facilitate targeted empathy generation in a mental health support domain. |
| Outcome: | The proposed approach achieves 7.6% improvement in BLEU, 36.7% reduction in Perplexity, and 7.6% increase in lexical diversity. |
What’s Hidden in a One-layer Randomly Weighted Transformer? (2021.emnlp-main)
Copied to clipboard
| Challenge: | Existing subnetworks of one-layer randomly weighted neural networks can achieve impressive performance without changing initializations. |
| Approach: | They find subnetworks within one-layer randomly weighted neural networks that can achieve impressive performance without ever modifying the initializations. |
| Outcome: | The proposed subnetworks match 98%/92% of the performance of a trained Transformersmall/base on IWSLT14/WMT14. |
Programmable Annotation with Diversed Heuristics and Data Denoising (2022.coling-1)
Copied to clipboard
| Challenge: | Neural natural language generation and understanding models require massive amounts of annotated data to be competitive. |
| Approach: | They propose a data programming framework that can jointly construct labeled data for language generation and understanding tasks by allowing annotators to modify an automatically-inferred alignment rule set between sequence labels and text. |
| Outcome: | The proposed framework generates high-quality data within a 1.48 BLEU and 6.42 slot F1 of 100% human-labeled data with just 100 labeled data samples outperforming benchmark annotation frameworks and other semi-supervised approaches. |
Reinforced Multi-task Approach for Multi-hop Question Generation (2020.coling-main)
Copied to clipboard
| Challenge: | Empirical evaluation shows our model to outperform the single-hop question generation models on both automatic evaluation metrics such as BLEU, METEOR, and ROUGE and human evaluation metrics for quality and coverage of the generated questions. |
| Approach: | They propose a question-aware reward function to maximize the utilization of supporting facts in the context. |
| Outcome: | The proposed model outperforms single-hop neural question generation models on automatic evaluation metrics and human evaluation metrics for quality and coverage of the generated questions. |
Selectively Answering Visual Questions (2024.findings-acl)
Copied to clipboard
| Challenge: | Large multi-modal models (LMMs) are capable of visual question answering (VQA) with unprecedented accuracy. |
| Approach: | They propose a calibration score that can be used to quantify uncertainty in visual question answering models. |
| Outcome: | The proposed calibration score is better calibrated than in text-only models for in-context learning. |
Addressing Semantic Drift in Question Generation for Semi-Supervised Question Answering (D19-1)
Copied to clipboard
| Challenge: | Existing QG models suffer from a “semantic drift” problem, i.e., the semantics of the model-generated question drifts away from the given context and answer. |
| Approach: | They propose two semantics-enhanced rewards obtained from downstream question paraphrasing and question answering tasks to regularize the QG model to generate semantically valid questions. |
| Outcome: | The proposed method achieves state-of-the-art performance w.r.t. traditional evaluation metrics and performs best on QA-based evaluation metrics. |
Toward Better Loanword Identification in Uyghur Using Cross-lingual Word Embeddings (C18-1)
Copied to clipboard
| Challenge: | Almost every natural language processing task suffers from data sparseness. |
| Approach: | They propose a method which identify loanwords in monolingual corpora by using cross-lingual word embeddings as core feature and a log-linear model which combines several shallow features to predict the final results. |
| Outcome: | The proposed method outperforms baseline models significantly on loanword identification and translation in four languages and eight translation directions. |
Recurrent Attention for Neural Machine Translation (2021.emnlp-main)
Copied to clipboard
| Challenge: | Recent research questions the importance of dot-product self-attention in Transformer models and shows that most attention heads learn simple positional patterns. |
| Approach: | They propose a novel mechanism to replace dot-product self-attention with a recurrent atteNtion mechanism that directly learns attention weights without token-to-token interaction. |
| Outcome: | The proposed model outperforms the Transformer model on translation tasks with fewer parameters and inference time. |
Bidimensional Leaderboards: Generate and Evaluate Language Hand in Hand (2022.naacl-main)
Copied to clipboard
Jungo Kasai, Keisuke Sakaguchi, Ronan Le Bras, Lavinia Dunagan, Jacob Morrison, Alexander Fabbri, Yejin Choi, Noah A. Smith
| Challenge: | Recent advances on models and metrics should benefit and inform each other, authors argue . bidimensional leaderboards allow for fast, accurate evaluation of language generation models . |
| Approach: | They propose a bidimensional leaderboard that tracks progress in language generation models and metrics for their evaluation. |
| Outcome: | The proposed leaderboards track progress in language generation models and metrics for their evaluation. |
NL2pSQL: Generating Pseudo-SQL Queries from Under-Specified Natural Language Questions (D19-1)
Copied to clipboard
| Challenge: | Existing studies focus on generating SQL codes from natural language questions . however, questions cover more diverse tasks including table manipulation or performance issues . |
| Approach: | They propose a task to generate pSQL codes from natural language questions . they define two new metrics suitable for the task, Canonical-BLEU and SQL-BLUE . |
| Outcome: | The proposed task generates well-formed queries on under-specified database issues. |
Sentence Mover’s Similarity: Automatic Evaluation for Multi-Sentence Texts (P19-1)
Copied to clipboard
| Challenge: | Existing automatic metrics for evaluating text are expensive and time-consuming. |
| Approach: | They propose automatic metrics that evaluate text in a continuous space using word and sentence embeddings. |
| Outcome: | The proposed method outperforms ROUGE on machine-generated summaries and human-authored essays on human-generated texts. |
Guiding Large Language Models to Post-Edit Machine Translation with Error Annotations (2024.findings-naacl)
Copied to clipboard
| Challenge: | supervised systems have not replaced dedicated supervised models for machine translation tasks. |
| Approach: | They propose to guide LLMs to post-edit MT with feedback from MQM annotations . they then fine-tune the LLM to improve its ability to exploit the feedback . |
| Outcome: | The proposed model improves TER, BLEU and COMET scores on Chinese-English, English-German and English-Russian data. |
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. |
Neural Machine Translation Incorporating Named Entity (C18-1)
Copied to clipboard
| Challenge: | Conventional NMT models have difficulty translating words with multiple meanings because of the high ambiguity. |
| Approach: | They propose a neural machine translation model that incorporates named entity (NE) tags of source-language sentences to reduce the difficulty in translating multiple meanings. |
| Outcome: | The proposed model achieves 3.11 point improvement in bilingual evaluation understudy (BLEU) on English-to-Japanese translation task with the ASPEC, and English- to-Bulgarian and English to-Romanian translation tasks with the Europarl corpus. |
Dynamic Programming Encoding for Subword Segmentation in Neural Machine Translation (2020.acl-main)
Copied to clipboard
| Challenge: | Empirical results on machine translation suggest that DPE is effective for segmenting output sentences. |
| Approach: | They propose a new algorithm for tokenizing sentences into subword units . they propose enabling exact log marginal likelihood estimation and exact MAP inference . |
| Outcome: | The proposed algorithm improves on machine translation datasets and on a large dataset. |
Rethinking Document-level Neural Machine Translation (2022.findings-acl)
Copied to clipboard
| Challenge: | Neural machine translation models are weak enough for document-level translation . current models only translate sentences individually, resulting in poor document coherence . |
| Approach: | They propose to use the original Transformer model to test document-level neural machine translation . they find that the original transformer models can achieve strong results for document translation if trained properly . |
| Outcome: | The proposed model outperforms sentence-level models on nine datasets and two sentence- level datasets across six languages. |
Geo-Aware Image Caption Generation (2020.coling-main)
Copied to clipboard
| Challenge: | Standard image caption generation systems do not take contextual information or world knowledge into account. |
| Approach: | They propose to build an image-specific representation of the geographic context and adapt the caption generation network to produce appropriate geographic names in the image descriptions. |
| Outcome: | The proposed system achieves significant improvements on a dataset that contains contextualized captions and geographic metadata and improves BLEU, ROUGE, METEOR and CIDEr scores. |
Generative Pretraining for Paraphrase Evaluation (2022.acl-long)
Copied to clipboard
| Challenge: | ParaBLEU is a paraphrase representation learning model and evaluation metric for text generation. |
| Approach: | They propose a paraphrase representation learning model and evaluation metric for text generation that uses generative conditioning as a pretraining objective. |
| Outcome: | The proposed model outperforms existing models on the 2017 WMT Metrics Shared Task using only 50% of the available training data and surpasses BLEU, ROUGE and METEOR with only 40 examples. |
Multilingual Mix: Example Interpolation Improves Multilingual Neural Machine Translation (2022.acl-long)
Copied to clipboard
| Challenge: | Existing approaches to train multilingual models to learn the inductive bias of a shared vocabulary and set of parameters across languages. |
| Approach: | They propose to use a multilingual crossover encoder-decoder to fuse language pairs at an instance level to encourage sharing of input and output spaces. |
| Outcome: | The proposed approach improves quality on English-to-Many, Many-to English and zero-shot translation tasks from +0.5 BLEU up to +5.5 BLUE points. |
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. |
Beyond Distillation: Task-level Mixture-of-Experts for Efficient Inference (2021.findings-emnlp)
Copied to clipboard
Sneha Kudugunta, Yanping Huang, Ankur Bapna, Maxim Krikun, Dmitry Lepikhin, Minh-Thang Luong, Orhan Firat
| Challenge: | Sparse Mixture-of-Experts (MoE) is a successful approach for scaling multilingual translation models to billions of parameters without a proportional increase in training computation. |
| Approach: | They propose to use a task-level routing approach to extract smaller, ready-to-deploy sub-networks from large sparse models by ignoring distillation. |
| Outcome: | Experiments on WMT and a web-scale dataset show that task-level routing outperforms token-level MoE models by +1.0 BLEU on average across 30 language pairs. |
Table-to-Text Generation with Effective Hierarchical Encoder on Three Dimensions (Row, Column and Time) (D19-1)
Copied to clipboard
| Challenge: | Seq2Seq models for table-to-text generation have achieved remarkable progress, but modeling table representation in one dimension is inadequate. |
| Approach: | They propose to model each table cell considering other records in the same row and to enrich table’s representation by modeling each cell in context of other cells in the similar column or with historical data respectively. |
| Outcome: | The proposed model outperforms baseline and state-of-the-art models on ROTOWIRE, a benchmark dataset of NBA basketball games. |
Neural Machine Translation of Text from Non-Native Speakers (N19-1)
Copied to clipboard
| Challenge: | Neural Machine Translation (NMT) systems are known to degrade when confronted with noisy data. |
| Approach: | They propose to augment training data with sentences containing artificially-introduced grammatical errors to make the system more robust to such errors. |
| Outcome: | The proposed approach recovers 1.0 BLEU out of 2.4 BLUE lost due to grammatical errors on a set of Spanish translations of the JFLEG grammar error correction corpus. |
Divide and Rule: Effective Pre-Training for Context-Aware Multi-Encoder Translation Models (2022.acl-long)
Copied to clipboard
| Challenge: | Multi-encoder models aim to improve translation quality by encoding document-level contextual information alongside the current sentence. |
| Approach: | They propose to pre-train contextual parameters over split sentence pairs to improve contextual encoding . they propose four different splitting methods to improve learning of contextual parameters . |
| Outcome: | The proposed model improves learning of contextual parameters, both in low and high resource settings. |
Retrieval-Augmented Machine Translation with Unstructured Knowledge (2025.findings-emnlp)
Copied to clipboard
| Challenge: | Retrieval-augmented generation (RAG) is a new approach to enhance large language models (LLMs). |
| Approach: | They propose a multi-task training method to teach LLMs how to use information from multilingual documents during their translation. |
| Outcome: | The proposed method improves LLMs by 1.6-3.1 BLEU and 1.0-2.0 COMET scores in En-Zh, and 1.7-2.9 BLUE and 2.1-2.7 COMET score in En de. |
COMET for Low-Resource Machine Translation Evaluation: A Case Study of English-Maltese and Spanish-Basque (2024.lrec-main)
Copied to clipboard
| Challenge: | Trainable metrics for machine translation evaluation have been scoring the highest correlations with human judgements in the meta-evaluations. |
| Approach: | They run a crowd-based evaluation campaign to evaluate COMET-22 and fine-tune it to improve its performance. |
| Outcome: | The proposed system outperforms BLEU and other lexical overlap metrics in the meta-evaluations. |
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. |
Improving the Factual Correctness of Radiology Report Generation with Semantic Rewards (2022.findings-emnlp)
Copied to clipboard
Jean-Benoit Delbrouck, Pierre Chambon, Christian Bluethgen, Emily Tsai, Omar Almusa, Curtis Langlotz
| Challenge: | Neural image-to-text radiology report generation systems have been successful on NLG metrics, but they are not factually complete or consistent due to inadequate training and evaluation. |
| Approach: | They propose a method to improve the factual completeness and correctness of generated radiology reports by using a dataset containing annotated chest X-ray images. |
| Outcome: | The proposed method significantly improves factual completeness and correctness of generated radiology reports on two open radiology report datasets. |
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 Reinforced Generation of Adversarial Examples for Neural Machine Translation (2020.acl-main)
Copied to clipboard
| Challenge: | Neural machine translation systems fail on less decent inputs, which may harm the credibility of these systems. |
| Approach: | They propose a paradigm that generates adversarial examples using reinforcement learning to expose pitfalls for a given performance metric. |
| Outcome: | The proposed paradigm produces stable attacks with meaning-preserving adversarial examples. |
A Simple and Effective Unified Encoder for Document-Level Machine Translation (2020.acl-main)
Copied to clipboard
| Challenge: | Existing models for document-level machine translation use two separate encoders to model the source sentences and document- level contexts. |
| Approach: | They propose a unified encoder that can outperform existing models of dual-encoder models . they propose to use document-level contexts to model the interaction between the contexts and the source sentences . |
| Outcome: | The proposed model outperforms baseline models of dual-encoder models in terms of BLEU and METEOR scores. |
Dynamically Adjusting Transformer Batch Size by Monitoring Gradient Direction Change (2020.acl-main)
Copied to clipboard
| Challenge: | Compared to previous studies, the performance of neural models is likely to be affected by the choice of hyper-parameters. |
| Approach: | They propose to automatically and dynamically determine batch sizes by accumulating gradients of mini-batches and performing an optimization step at just the time when the direction of gradients starts to fluctuate. |
| Outcome: | The proposed approach improves the Transformer model with a fixed 25k batch size by +0.73 and +0.82 BLEU respectively. |
Towards More Fine-grained and Reliable NLP Performance Prediction (2021.eacl-main)
Copied to clipboard
| Challenge: | Performance prediction is a task of estimating a system’s performance without performing experiments. |
| Approach: | They propose to understand reliability of performance prediction models from two angles: confidence intervals and calibration. |
| Outcome: | The proposed methods demonstrate the feasibility of fine-grained performance prediction and the necessity to perform reliability analysis for performance prediction methods in the future. |
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. |
Evaluating Subtitle Segmentation for End-to-end Generation Systems (2022.lrec-1)
Copied to clipboard
| Challenge: | Subtitle segmentation can be evaluated with sequence segmentation metrics against a human reference, but cannot be applied when systems generate outputs different than the reference, e.g. with end-to-end subtitling systems. |
| Approach: | They propose to use Sigma to evaluate subtitle segmentation against a human reference and a boundary projection method to disentangle the effect of good segmentation from text quality. |
| Outcome: | The proposed method disentangles the effect of good segmentation from text quality and is compared with existing metrics. |
Understanding and Improving the Robustness of Terminology Constraints in Neural Machine Translation (2023.acl-long)
Copied to clipboard
| Challenge: | Existing terminology constraint test sets are blind to this issue due to oversimplified settings . PH methods retain high constraint accuracy but lower translation quality . |
| Approach: | They propose a method that replaces terminology terms with ordered labels . placeholder methods are better at retaining high constraint accuracy but lower translation quality . |
| Outcome: | The proposed method achieves high accuracy and translation quality regardless of the number or length of constraints. |
SrcMix: Mixing of Related Source Languages Benefits Extremely Low-resource Machine Translation (2026.findings-eacl)
Copied to clipboard
| Challenge: | Multilingual models are widely used for machine translation, but their effectiveness for extremely low-resource languages (ELRLs) is dependent on how related languages are incorporated during fine-tuning. |
| Approach: | They propose a source-side mixing strategy that combines related ELRLs during fine-tuning while constraining the decoder to a single target language. |
| Outcome: | The proposed approach improves performance in high-resource to ELRL translations and in mid-resourced to MT translations. |
Accelerating Asynchronous Stochastic Gradient Descent for Neural Machine Translation (D18-1)
Copied to clipboard
| Challenge: | In order to achieve faster training we increase the mini-batch size and scale the learning rate accordingly. |
| Approach: | They propose a technique that delays gradient updates by increasing the mini-batch size to improve the model's convergence. |
| Outcome: | The proposed technique can train a shallow machine translation system 27% faster than an optimized baseline with negligible penalty in BLEU. |
IW-Bench: Evaluating Large Multimodal Models for Converting Image-to-Web (2025.findings-acl)
Copied to clipboard
Hongcheng Guo, Wei Zhang, Junhao Chen, Yaonan Gu, Jian Yang, Junjia Du, Shaosheng Cao, Binyuan Hui, Tianyu Liu, Jianxin Ma, Chang Zhou, Zhoujun Li
| Challenge: | Existing models have been introduced to improve image comprehension, but there is no robust benchmark for imagetoweb conversion. |
| Approach: | They propose a benchmark to assess imagetoweb conversion proficiency of large multimodal models . they propose to measure layout information of web pages by parsing the Document Object Model tree . |
| Outcome: | The proposed benchmark measures the layout information of web pages—i.e., the positional relationships between elements—which has been overlooked by prior work. |
AfriMTE and AfriCOMET: Enhancing COMET to Embrace Under-resourced African Languages (2024.naacl-long)
Copied to clipboard
Jiayi Wang, David Adelani, Sweta Agrawal, Marek Masiak, Ricardo Rei, Eleftheria Briakou, Marine Carpuat, Xuanli He, Sofia Bourhim, Andiswa Bukula, Muhidin Mohamed, Temitayo Olatoye, Tosin Adewumi, Hamam Mokayed, Christine Mwase, Wangui Kimotho, Foutse Yuehgoh, Anuoluwapo Aremu, Jessica Ojo, Shamsuddeen Muhammad, Salomey Osei, Abdul-Hakeem Omotayo, Chiamaka Chukwuneke, Perez Ogayo, Oumaima Hourrane, Salma El Anigri, Lolwethu Ndolela, Thabiso Mangwana, Shafie Mohamed, Hassan Ayinde, Oluwabusayo Awoyomi, Lama Alkhaled, Sana Al-azzawi, Naome Etori, Millicent Ochieng, Clemencia Siro, Njoroge Kiragu, Eric Muchiri, Wangari Kimotho, Toadoum Sari Sakayo, Lyse Naomi Wamba, Daud Abolade, Simbiat Ajao, Iyanuoluwa Shode, Ricky Macharm, Ruqayya Iro, Saheed Abdullahi, Stephen Moore, Bernard Opoku, Zainab Akinjobi, Abeeb Afolabi, Nnaemeka Obiefuna, Onyekachi Ogbu, Sam Ochieng’, Verrah Otiende, Chinedu Mbonu, Yao Lu, Pontus Stenetorp
| Challenge: | Recent advances in machine translation (MT) have focused on scaling multilingual machine translation models and evaluation data to hundreds of languages, including multiple under-resourced languages. |
| Approach: | They propose to use n-gram matching metrics to measure progress in multilingual machine translation to 13 typologically diverse African languages to create high-quality human evaluation data with simplified MQM guidelines. |
| Outcome: | The proposed metrics have a higher correlation with human judgments than n-gram matching metrics such as BLEU and METEOR. |
Generating Accurate Electronic Health Assessment from Medical Graph (2020.findings-emnlp)
Copied to clipboard
| Challenge: | Existing models based on medical domain-specific knowledge or patients’ prior diagnoses and clinical encounters were mainly based upon clinical diagnoses. |
| Approach: | They propose a graph neural network model that incorporates clinical knowledge into an end-to-end corpus-learning system and builds on it. |
| Outcome: | The proposed model significantly improves the BLEU and rouge score compared with baseline models and physicians’ evaluation showed that it generates high-quality assessments. |
QSTS: A Question-Sensitive Text Similarity Measure for Question Generation (2022.coling-1)
Copied to clipboard
| Challenge: | Existing measures for question generation have been inadequately evaluated . current research uses QA datasets containing pairs of (reference question, passage context) elements. |
| Approach: | They propose a Question-Sensitive Text Similarity measure for comparing two questions . they also propose enabling question similarity research in QG contexts by using a dataset called SimQG. |
| Outcome: | The proposed measure overcomes shortcomings of existing measures that depend on n-gram overlap scores and obtains superior results compared to existing measures on publicly-available QG datasets. |
Training Deeper Neural Machine Translation Models with Transparent Attention (D18-1)
Copied to clipboard
| Challenge: | Existing NMT models are shallow in comparison to convolutional models used for both text and vision tasks. |
| Approach: | They propose to modify the attention mechanism to ease the optimization of deeper models by a simple modification to the seq2seq with attention paradigm. |
| Outcome: | The proposed model achieves consistent gains of 0.7-1.1 BLEU on the benchmark WMT’14 English-German and WMT'15 Czech-English tasks. |
Measuring Robustness for NLP (2022.coling-1)
Copied to clipboard
| Challenge: | Existing methods to evaluate NLP models are limited to news domains and cannot be generalized to other domains. |
| Approach: | They propose a measure of NLP quality based on robustness . they measure consistency of cross-domain accuracy and introduce coefficient of variation and gamma-Robustness based upon human evaluation . |
| Outcome: | The proposed approach shows higher agreement with human evaluation than accuracy scores on ranking machine translation systems. |
SDS-200: A Swiss German Speech to Standard German Text Corpus (2022.lrec-1)
Copied to clipboard
Michel Plüss, Manuela Hürlimann, Marc Cuny, Alla Stöckli, Nikolaos Kapotis, Julia Hartmann, Malgorzata Anna Ulasik, Christian Scheller, Yanick Schraner, Amit Jain, Jan Deriu, Mark Cieliebak, Manfred Vogel
| Challenge: | Using a web recording tool, participants were asked to translate their Swiss German text to their own dialect before recording it. |
| Approach: | They present a corpus of Swiss German dialectal speech with Standard German text translations . the dataset allows for training speech translation, dialect recognition, and speech synthesis systems . |
| Outcome: | The dataset allows for training speech translation, dialect recognition, and speech synthesis systems. |
Mathematical Word Problem Generation from Commonsense Knowledge Graph and Equations (2021.emnlp-main)
Copied to clipboard
| Challenge: | Existing models for generating mathematical word problems are lacking in educational assessment. |
| Approach: | They propose an end-to-end neural model to generate diverse mathematical word problems from commonsense knowledge graph and equations. |
| Outcome: | The proposed model outperforms the SOTA models in terms of evaluation metrics and topic relevance. |
Fluent and Low-latency Simultaneous Speech-to-Speech Translation with Self-adaptive Training (2020.findings-emnlp)
Copied to clipboard
| Challenge: | Current approaches to simultaneous speech-to-speech translation accumulate more and more latencies in later sentences when the speaker talks faster. |
| Approach: | They propose a method which generates more fluent target speech latency than the baseline . they propose to use self-adaptive translation to adjust the length of translations to accommodate different source speech rates. |
| Outcome: | Xiong et al., 2019) show that the proposed method generates more fluent target speech latency than baseline . authors say it provides more natural communication process than speech-to-text translation . xiong and colleagues say the proposed technique is more efficient than current approaches . |
Multi-Reference Training with Pseudo-References for Neural Translation and Text Generation (D18-1)
Copied to clipboard
| Challenge: | Neural text generation has been quite successful recently, but during training time, only one reference is considered for each example, even though there are often multiple references available. |
| Approach: | They propose an algorithm to generate exponentially many pseudo-references by compressing existing references into lattices and traversing them to generate new pseudo-References. |
| Outcome: | The proposed model significantly improves on baselines in machine translation and image captioning, and is comparable to existing models. |
Alternative Input Signals Ease Transfer in Multilingual Machine Translation (2022.acl-long)
Copied to clipboard
| Challenge: | Recent work in multilingual machine translation (MMT) has focused on the potential of positive transfer between languages. |
| Approach: | They propose to augment training data with alternative signals that unify different writing systems, such as phonetic, romanized, and transliterated input. |
| Outcome: | The proposed model outperforms strong ensemble baselines on Indic and Turkic languages by 1.3 BLEU points on both languages. |
Adapting Word Embeddings to New Languages with Morphological and Phonological Subword Representations (D18-1)
Copied to clipboard
| Challenge: | Existing approaches to generalization to resource-rich languages are difficult . a recent study shows that word representations can be useful in low resource languages . |
| Approach: | They propose two approaches for improving generalization to low-resource languages by adapting continuous word representations using linguistically motivated subword units. |
| Outcome: | The proposed method improves generalization to low resource languages . it requires neither parallel corpora nor bilingual dictionaries and requires no parallel training . |
Structural Neural Encoders for AMR-to-text Generation (N19-1)
Copied to clipboard
| Challenge: | Abstract Meaning Representation (AMR) graphs are graphs, rather than trees, because they contain reentrant nodes with multiple parents. |
| Approach: | They propose to use sequence-to-sequence models that encode AMR graphs into vector representations to generate sentences from AMRs. |
| Outcome: | The proposed model outperforms tree encoders in the AMR-to-text generation task by 24.40 points. |
A Streaming Approach For Efficient Batched Beam Search (2020.emnlp-main)
Copied to clipboard
| Challenge: | During decoding, candidates terminate or are pruned according to heuristics, a streaming method is used to "refill" the batch after it finishes translating some fraction of the current batch. |
| Approach: | They propose an efficient batching strategy for variable-length decoding on GPU architectures by streamlining the batching process. |
| Outcome: | The proposed method reduces runtime by 71% compared to a fixed-width beam search baseline and 17% compared with a variable-widness baseline while matching baselines’ BLEU. |
Cross-modal Contrastive Learning for Speech Translation (2022.naacl-main)
Copied to clipboard
| Challenge: | Existing approaches for speech translation focus on using additional data from MT and automatic speech recognition (ASR). |
| Approach: | They propose a cross-modal contrastive learning method for end-to-end speech-totext translation. |
| Outcome: | The proposed method outperforms existing methods on a popular benchmark MuST-C. |
Penalizing Divergence: Multi-Parallel Translation for Low-Resource Languages of North America (2022.coling-1)
Copied to clipboard
| Challenge: | Existing studies show that multi-parallel translation models can overfit when training data are limited. |
| Approach: | They introduce a regularizer which penalizes translation models when they represent source sentences with identical target translations in divergent ways. |
| Outcome: | The proposed model improves when the target data for all language pairs are identical. |
Evaluating Coherence in Dialogue Systems using Entailment (N19-1)
Copied to clipboard
| Challenge: | Evaluating open-domain dialogue systems is difficult due to the diversity of possible correct answers. |
| Approach: | They propose a set of metrics for evaluating topic coherence using distributed sentence representations and calculable approximations of human judgment using conversational coherency. |
| Outcome: | The proposed metrics can be used as a surrogate for human judgment based on conversational coherence on large-scale datasets and provide an unbiased estimate for the quality of the responses. |
Logic-Consistency Text Generation from Semantic Parses (2021.findings-acl)
Copied to clipboard
| Challenge: | Text generation from semantic parses is challenging due to the complexity of the inner logic and the lack of automatic evaluation metrics for logic consistency. |
| Approach: | They propose a framework for logic consistent text generation from semantic parses that employs iterative training procedures and quality control. |
| Outcome: | The proposed framework enhances logic consistency and human evaluation on two benchmark datasets. |
Leakage-Adjusted Simulatability: Can Models Generate Non-Trivial Explanations of Their Behavior in Natural Language? (2020.findings-emnlp)
Copied to clipboard
| Challenge: | Existing models that generate NL explanations for tasks have been evaluated on the basis of surface-level similarities to human explanations, both through automatic metrics like BLEU and human evaluations. |
| Approach: | They propose to use a model as a proxy for a human observer to evaluate NL explanations from the model simulatability perspective. |
| Outcome: | The proposed model-generated explanations are evaluated on the basis of surface-level similarities to human explanations, both through automatic metrics like BLEU and human evaluations. |
Structuring Radiology Reports: Challenging LLMs with Lightweight Models (2025.emnlp-main)
Copied to clipboard
Johannes Moll, Louisa Fay, Asfandyar Azhar, Sophie Ostmeier, Sergios Gatidis, Tim C. Lueth, Curtis Langlotz, Jean-Benoit Delbrouck
| Challenge: | Radiology reports lack a standardized format, limiting both interpretability and machine learning applications. |
| Approach: | They propose to use lightweight encoder-decoder models for structuring radiology reports . they compare models with eight open-source LLMs with prompting and in-context learning . |
| Outcome: | The proposed models outperform eight open-source LLMs on a human-annotated test set. |
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. |
Meta-Learning for Low-Resource Neural Machine Translation (D18-1)
Copied to clipboard
| Challenge: | In this paper, we propose to extend the recently introduced model-agnostic meta-learning algorithm for low-resource neural machine translation (NMT). |
| Approach: | They propose to extend the recently introduced meta-learning algorithm for low-resource neural machine translation (NMT) they frame low-Resource translation as a meta- learning problem where we learn to adapt to low-REsource languages based on multilingual high-resourced language tasks. |
| Outcome: | The proposed meta-learning algorithm outperforms the multilingual, transfer learning based approach and can train a competitive NMT system with only a fraction of training examples. |
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. |
CaLcs: Continuously Approximating Longest Common Subsequence for Sequence Level Optimization (D18-1)
Copied to clipboard
| Challenge: | Maximum-likelihood estimation (MLE) is widely used for text-generation based natural language processing applications. |
| Approach: | They propose a method to train models with maximum-likelihood estimation using a differentiable surrogate of longest common subsequence measure that captures sequence-level structure similarity. |
| Outcome: | Experimental results show that the proposed approach improves on the current MLE approach for downstream tasks like text summarization and machine translation. |
Pre-trained language model representations for language generation (N19-1)
Copied to clipboard
| Challenge: | Pre-trained language model representations have been successful in a wide range of language understanding tasks. |
| Approach: | They propose to use pre-trained language model representations to integrate them into sequence to sequence models and apply it to machine translation and abstractive summarization. |
| Outcome: | The proposed model is able to perform 5.3 BLEU in machine translation and 5.3 on the full text version of CNN/DailyMail. |
Improving Factual Completeness and Consistency of Image-to-Text Radiology Report Generation (2021.naacl-main)
Copied to clipboard
| Challenge: | Existing report generation systems suffer from incomplete and inconsistent generation, despite achieving high performance on natural language metrics such as CIDEr and BLEU. |
| Approach: | They propose two new rewards that encourage the generation of factually complete and consistent radiology reports by using an existing semantic equivalence metric. |
| Outcome: | The proposed system significantly improves the F1 score of a clinical information extraction performance on two open radiology report datasets. |
A Human Evaluation of AMR-to-English Generation Systems (2020.coling-main)
Copied to clipboard
| Challenge: | a recent human evaluation of AMR generation systems is compared to automated metrics. |
| Approach: | They propose a human evaluation which collects fluency and adequacy scores and categorization of error types for AMR generation systems. |
| Outcome: | The results show that human evaluations are more nuanced than automated metrics. |
Modeling Consistency Preference via Lexical Chains for Document-level Neural Machine Translation (2022.emnlp-main)
Copied to clipboard
| Challenge: | Experimental results show that consistency preference for lexical chains reduces lexical translation inconsistency . Lexical translation consistency is a common discourse phenomenon . |
| Approach: | They propose a consistency-aware model which captures consistency context . they then define consistency-tailored latent variables which guide translation of corresponding sentences . |
| Outcome: | The proposed model significantly improves translation performance in ChineseEnglish and FrenchEnglish translation tasks. |
RQUGE: Reference-Free Metric for Evaluating Question Generation by Answering the Question (2023.findings-acl)
Copied to clipboard
Alireza Mohammadshahi, Thomas Scialom, Majid Yazdani, Pouya Yanki, Angela Fan, James Henderson, Marzieh Saeidi
| Challenge: | Existing metrics for evaluating the quality of automatically generated questions are expensive and penalise valid questions that may not have high lexical or semantic similarity to the reference questions. |
| Approach: | They propose a question-answering and span scorer metric based on the answerability of the candidate question given the context. |
| Outcome: | The proposed metric has higher correlation with human judgment without relying on the reference question. |
Towards a Better Metric for Evaluating Question Generation Systems (D18-1)
Copied to clipboard
| Challenge: | Existing evaluation metrics based on n-gram similarity do not correlate well with human judgments . large datasets for document Question Answering (QA) have enabled the development of end-to-end supervised models . |
| Approach: | They propose a scoring function to capture answerability of questions . they also integrate existing similarity metrics into the scoring function . |
| Outcome: | The proposed scoring function improves human judgments on question answerability . the proposed scoring functions are made publicly available . |
TranSFormer: Slow-Fast Transformer for Machine Translation (2023.findings-acl)
Copied to clipboard
| Challenge: | Prior work has focused on treating subwords as basic units in developing such systems. |
| Approach: | They propose a slow-fast two-stream learning model that uses a “slow” branch to deal with subword sequences and a "fast" branch to cope with longer character sequences. |
| Outcome: | The proposed model shows consistent BLEU improvements (larger than 1 BLUE point) on several machine translation benchmarks. |
Extremely Low Bit Transformer Quantization for On-Device Neural Machine Translation (2020.findings-emnlp)
Copied to clipboard
Insoo Chung, Byeongwook Kim, Yoonjung Choi, Se Jung Kwon, Yongkweon Jeon, Baeseong Park, Sangha Kim, Dongsoo Lee
| Challenge: | Quantization is an effective technique to address heavy computation load and memory overhead during inference. |
| Approach: | They propose a low-bit quantization strategy to represent Transformer weights by an extremely low number of bits. |
| Outcome: | The proposed model achieves 11.8 smaller model size than baseline model, with less than -0.5 BLEU. |
Multimodal Differential Network for Visual Question Generation (D18-1)
Copied to clipboard
| Challenge: | Current dialog systems show improvement in visual question answering but this does not translate to improved human-AI dialog. |
| Approach: | They propose to use a Multimodal Differential Network to generate natural questions from images using a multimodal differential network. |
| Outcome: | The proposed approach significantly improves over state-of-the-art benchmarks on the quantitative metrics. |
Breaking the Representation Bottleneck of Chinese Characters: Neural Machine Translation with Stroke Sequence Modeling (2022.emnlp-main)
Copied to clipboard
| Challenge: | Existing research treats Chinese character as a minimum unit for representation . however, such representation suffers from two bottlenecks: 1) learning bottleneck; 2) parameter bottleneck, each individual character has to be represented by a unique vector. |
| Approach: | They propose a representation method for Chinese characters to break the representation bottlenecks . they map each stroke to a specific Latin character, thus allowing similar Chinese characters . |
| Outcome: | The proposed representation method breaks two representation bottlenecks in Chinese character representation . it maps each stroke to a specific Latin character, thus allowing similar Chinese characters to have similar representations . |
Universal Conditional Masked Language Pre-training for Neural Machine Translation (2022.acl-long)
Copied to clipboard
| Challenge: | Pre-trained sequence-to-sequence models have significantly improved Neural Machine Translation (NMT) this paper demonstrates that pre-training a sequence- to-squence model with a bidirectional decoder can produce notable performance gains for both Autoregressive and Non-autoregressive NMT tasks. |
| Approach: | They propose a conditional masked language model pre-trained on bilingual and monolingual corpora in many languages. |
| Outcome: | The proposed model can achieve significant performance improvements on all scenarios from low- to extremely high-resource languages. |
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. |
Imitation Attacks and Defenses for Black-box Machine Translation Systems (2020.emnlp-main)
Copied to clipboard
| Challenge: | Using simulated experiments, we demonstrate that MT systems can be stolen even when imitation models have different input data or architectures than their target models. |
| Approach: | They propose a defense that modifies translation outputs to misdirect optimization of imitation models. |
| Outcome: | The proposed defense degrades the adversary’s BLEU score and attack success rate at some cost in the defender’s performance and inference speed. |
Disentangling Pretrained Representation to Leverage Low-Resource Languages in Multilingual Machine Translation (2024.lrec-main)
Copied to clipboard
| Challenge: | Multilingual neural machine translation requires an enormous dataset, leaving the low-resource language (LRL) underdeveloped. |
| Approach: | They evaluated five languages using a parallel corpus of 1,000 instances each and found a zero-shot improvement of 7.4 from the baseline score of 7.1 to a score of 15.5 at best. |
| Outcome: | The proposed model improves performance in the linguistically diverse country of Indonesia by 7.4 from baseline score of 7.1 to 15.5 at best. |
SemBleu: A Robust Metric for AMR Parsing Evaluation (P19-1)
Copied to clipboard
| Challenge: | Abstract Meaning Representation (AMR) is a semantic formalism where the meaning of a sentence is encoded as a rooted, directed graph. |
| Approach: | They propose a metric that extends SMATCH to parse AMRs and does not suffer from search errors. |
| Outcome: | The proposed metric does not suffer from search errors and considers non-local correspondences in addition to local ones. |
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. |
Sequence-Level Mixed Sample Data Augmentation (2020.emnlp-main)
Copied to clipboard
| Challenge: | Despite their empirical success, neural networks still have difficulty capturing compositional aspects of natural language. |
| Approach: | They propose a data augmentation approach to encourage compositional behavior in neural networks . they propose to softly combine input/output sequences from the training set . |
| Outcome: | The proposed approach yields 1.0 BLEU improvement on translation datasets over baselines. |
Reranking for Neural Semantic Parsing (P19-1)
Copied to clipboard
| Challenge: | Semantic parsing is the task of transducing natural language utterances into machine executable meaning representations (e.g., Python code). |
| Approach: | They propose to rerank an n-best list of predicted MRs and use features to fix observed problems with baseline models to improve parser performance. |
| Outcome: | The proposed method outperforms the best published neural parser on four datasets and improves the baseline parsing performance by 5.7% and 2.9%. |
Speeding up Transformer Decoding via an Attention Refinement Network (2022.coling-1)
Copied to clipboard
| Challenge: | Extensive experiments on ten WMT machine translation tasks show that the proposed model yields an average of 1.35x faster (with almost no decrease in BLEU) |
| Approach: | They propose a weighted residual network which reconstructs attention by reusing the features across layers. |
| Outcome: | The proposed model is 1.35x faster than the state-of-the-art inference model on translation tasks compared to AAN and SAN models with fewer parameter numbers . |
Training Data Augmentation for Code-Mixed Translation (2021.naacl-main)
Copied to clipboard
| Challenge: | We show a 5.8 point increase in BLEU on heavily code-mixed sentences . code-mixing is becoming more commonplace in several bilingual communities . |
| Approach: | They propose a method to convert existing parallel data sources into code-mixed parallel data. |
| Outcome: | The proposed method shows a 5.8 point increase in BLEU on heavily code-mixed sentences on a Hindi-English code-mixed translation task. |
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. |
GECOR: An End-to-End Generative Ellipsis and Co-reference Resolution Model for Task-Oriented Dialogue (D19-1)
Copied to clipboard
| Challenge: | Ellipsis and co-reference are common and ubiquitous especially in multi-turn dialogues. |
| Approach: | They propose a unified end-to-end Generative Ellipsis and CO-reference Resolution model . the model can generate a new pragmatically complete user utterance by alternating the generation and copy mode for each user . |
| Outcome: | The proposed model can generate a new pragmatically complete user utterance by alternating the generation and copy mode for each user . intrinsic evaluations on the resolution of ellipsis and co-reference show that the model outperforms the baseline model in terms of EM, BLEU and F1 . |
Con-NAT: Contrastive Non-autoregressive Neural Machine Translation (2022.findings-emnlp)
Copied to clipboard
| Challenge: | Neural machine translation models are autoregressive, which means they predict tokens one by one based on source tokens and previously predicted tokens. |
| Approach: | They propose a conditional masked language model which incorporates contrastive learning into the conditional language model. |
| Outcome: | The proposed model improves on WMT’16 Ro-En translation directions with different data sizes. |
NSL-MT: Linguistically Informed Negative Samples for Efficient Machine Translation in African Low-Resource Languages (2026.findings-acl)
Copied to clipboard
| Challenge: | In low-resource settings, models encounter too few examples to reliably distinguish grammatical patterns from noise. |
| Approach: | They propose a negative space learning machine translation (NSL-MT) method that augments limited parallel data with synthetically generated violations of the target language’s grammar and explicitly penalizes the model when it assigns high probability to these violations. |
| Outcome: | The proposed method delivers 3-12% BLEU gains for well-performing models and 56-89% gains for models lacking decent initial support. |
Improving Simultaneous Translation by Incorporating Pseudo-References with Fewer Reorderings (2021.emnlp-main)
Copied to clipboard
| Challenge: | Existing systems for simultaneous translation are still trained on full-sentence bitexts due to the abundance of unnecessary long-distance reorderings. |
| Approach: | They propose to rewrite target side of existing full-sentence corpora into simultaneous-style translation by adding generated pseudo-references to the target side. |
| Outcome: | Experiments on ZhEn and JaEn simultaneous translation show that the proposed method improves on existing full-sentence corpora. |
Iterative Domain-Repaired Back-Translation (2020.emnlp-main)
Copied to clipboard
| Challenge: | Existing studies show that NMT models perform poorly in specific domains when in-domain parallel corpora are scarce or nonexistent. |
| Approach: | They propose an iterative domain-repaired back-translation framework to refine translations in bilingual data by round-trip translating monolingual sentences. |
| Outcome: | The proposed framework achieves 15.79 and 4.47 BLEU improvements over unadapted models and back-translation in domain-specific translations. |
Hypoformer: Hybrid Decomposition Transformer for Edge-friendly Neural Machine Translation (2022.emnlp-main)
Copied to clipboard
| Challenge: | Existing methods to compress Transformer are limited to sub-components, e.g., selfattention networks or embedding layer. |
| Approach: | They propose a Hybrid Tensor-Train decomposition which retains full rank and meanwhile reduces operations and parameters. |
| Outcome: | The proposed model outperforms light-weight SOTA methods on three translation tasks and achieves 7.1 points absolute improvement in BLEU and 1.27 X speedup on IWSLT’14 De-En task. |
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. |
Data and Parameter Scaling Laws for Neural Machine Translation (2021.emnlp-main)
Copied to clipboard
| Challenge: | Recent work shows that supervised neural machine translation models scale like a power law with the amount of training data and number of non-embedding parameters in the model. |
| Approach: | They show that cross-entropy loss of supervised neural machine translation models scales like a power law with the amount of training data and number of non-embedding parameters in the model. |
| Outcome: | The proposed model can predict BLEU and ROI of labeling data in low-resource language pairs. |
Handling Divergent Reference Texts when Evaluating Table-to-Text Generation (P19-1)
Copied to clipboard
| Challenge: | Existing text generation metrics rely on reference texts, such as BLEU and ROUGE, but they are too expensive to apply repeatedly. |
| Approach: | They propose a metric which aligns n-grams from the generated texts to the semi-structured data before computing their precision and recall. |
| Outcome: | The proposed metric correlates with human judgments better than existing text generation metrics while being easier to use. |
Autoregressive Knowledge Distillation through Imitation Learning (2020.emnlp-main)
Copied to clipboard
| Challenge: | Autoregressive models are ubiquitous in natural language processing due to the sequential nature of text generation. |
| Approach: | They propose a compression technique for autoregressive models driven by an imitation learning perspective on knowledge distillation. |
| Outcome: | The proposed method outperforms other distillation algorithms on translation and summarization tasks while increasing inference speed 14 times. |
HOLMS: Alternative Summary Evaluation with Large Language Models (2020.coling-main)
Copied to clipboard
| Challenge: | Efficient document summarization requires evaluation measures that can rank a set of systems based on an average score and highlight which individual summary is better than another. |
| Approach: | They propose a hybrid evaluation measure for document summarization called HOLMS that combines both language models pre-trained on large corpora and lexical similarity measures. |
| Outcome: | The proposed measure outperforms ROUGE and BLEU on several extractive summarization datasets for both linguistic quality and pyramid scores. |
On the Importance of Diversity in Question Generation for QA (2020.acl-main)
Copied to clipboard
| Challenge: | In this paper, we show that textual diversity in automatic question generation is beneficial for downstream QA. |
| Approach: | They propose to use textual diversity to promote automatic question generation as a quality measure for QA. |
| Outcome: | The proposed measure of QG quality correlates well with evaluation on QA. |
Table-To-Text generation and pre-training with TabT5 (2022.findings-emnlp)
Copied to clipboard
| Challenge: | Large language models (LLMs) are limited when it comes to structured or semi-structured domains like tables. |
| Approach: | They propose an encoder-decoder model that generates natural language text based on tables and textual inputs. |
| Outcome: | TabT5 achieves 15% increase in sequence accuracy on spreadsheet formula prediction and data-to-text generation domains. |
CoMix: Guide Transformers to Code-Mix using POS structure and Phonetics (2023.findings-acl)
Copied to clipboard
| Challenge: | Existing multilingual transformer models lack the ability to intermix words of one language into the structure of another. |
| Approach: | They propose a pretraining approach to improve representation of code-mixed data in transformer models by incorporating phonetic signals, a modified attention mechanism and weak supervision guided generation by parts-of-speech constraints. |
| Outcome: | The proposed model improves performance across four code-mixed tasks and generalizes on out-of-domain translation. |
A Tree-based Decoder for Neural Machine Translation (D18-1)
Copied to clipboard
| Challenge: | Existing work on adding syntactic information to NMT systems is limited to linguistically-inspired tree structures. |
| Approach: | They propose an NMT model that can naturally generate the topology of an arbitrary tree structure on the target side. |
| Outcome: | The proposed model outperforms standard seq2seq models by 2.1 BLEU points and other methods for incorporating target-side syntax by 0.7 BLUE points. |
Language Model Augmented Relevance Score (2021.acl-long)
Copied to clipboard
| Challenge: | Existing metrics that compare the candidate with the human reference do not consider the context, resulting in poor correlation with human judgements. |
| Approach: | They propose a language model-aware metric that augments the human reference while considering the context to provide evaluation scores that correlate highly with human judgements. |
| Outcome: | The proposed metric achieves higher correlation with human reference judgements and differentiates well-formed candidates from adversarial samples to a larger degree. |
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. |
Boosting Code Summarization by Embedding Code Structures (2022.coling-1)
Copied to clipboard
| Challenge: | Recent work on code summarization relies on structural information from the abstract syntax tree (AST) of source codes. |
| Approach: | They propose a program dependency graph (PDG) that represents the structure of a code more effectively. |
| Outcome: | The proposed model improves the performance of an out-of-domain benchmark dataset and the measure SBERT score. |
JPG - Jointly Learn to Align: Automated Disease Prediction and Radiology Report Generation (2022.coling-1)
Copied to clipboard
| Challenge: | Existing methods rarely consider cross-modal alignment between textual and visual features and ignore disease tags as auxiliary for report generation. |
| Approach: | They propose a "Jointly learning framework for automated disease Prediction and radiology report Generation" the framework integrates cross-modal alignment between textual and visual features and disease tags to improve the quality of reports. |
| Outcome: | The proposed framework improves the quality of radiology reports by combining the main task and auxiliary tasks. |
Better Sign Language Translation with STMC-Transformer (2020.coling-main)
Copied to clipboard
| Challenge: | Current SLT approaches use a sign language recognition system to extract sign language glosses from videos. |
| Approach: | They propose to use a Sign Language Recognition system to extract sign language glosses from videos and a translation system to generate spoken language translations from the glossed sign language. |
| Outcome: | The proposed system outperforms existing methods on gloss-to-text and video-to text translations on the ASLG-PC12 corpus. |
Adapting Multilingual Models for Code-Mixed Translation (2022.findings-emnlp)
Copied to clipboard
| Challenge: | Prior work has addressed the lack of gold standard code-mixed to pure language parallel data with data augmentation techniques. |
| Approach: | They propose a back-translation-based training scheme for code-mixed translation which eliminates dependence on external resources. |
| Outcome: | The proposed model beats previous work by up to +3.8 BLEU on code-mixed tasks. |
Multilingual Unsupervised Neural Machine Translation with Denoising Adapters (2021.emnlp-main)
Copied to clipboard
| Challenge: | Multilingual unsupervised machine translation is a computationally expensive and hard to tune approach . auxiliary parallel data is used to train translation systems from monolingual data . |
| Approach: | They propose to use auxiliary parallel language pairs to train unsupervised machine translations . they propose to add auxiliary languages to pre-trained mBART-50 models with denoising adapters . |
| Outcome: | The proposed approach is on-par with back-translation and allows adding unseen languages incrementally. |
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. |
CHIA: CHoosing Instances to Annotate for Machine Translation (2022.findings-emnlp)
Copied to clipboard
| Challenge: | Neural machine translation systems perform poorly on low-resource language pairs, for which large-scale parallel data is unavailable. |
| Approach: | They propose a method for selecting instances to annotate for machine translation using existing multi-way parallel datasets. |
| Outcome: | The proposed method outperforms unsupervised methods on 20 languages and a multi-way parallel dataset on high-resource languages. |
Improving NMT Models by Retrofitting Quality Estimators into Trainable Energy Loss (2025.coling-main)
Copied to clipboard
| Challenge: | Reinforcement learning has shown great promise in aligning language models with human preferences in a variety of text generation tasks, including machine translation. |
| Approach: | They propose a method that employs quality estimators as trainable loss networks to backpropagate to the NMT model. |
| Outcome: | The proposed method outperforms strong baselines and proximal policy optimizations on English-to-Mongolian translation. |
Scientific Credibility of Machine Translation Research: A Meta-Evaluation of 769 Papers (2021.acl-long)
Copied to clipboard
| Challenge: | a meta-evaluation of machine translation (MT) has been conducted in 769 research papers . a recent study shows that evaluation practices have changed over the past decade . |
| Approach: | They propose a meta-evaluation method for machine translation that uses BLEU scores to evaluate MT performance. |
| Outcome: | The proposed meta-evaluation of machine translation shows that evaluation practices have changed over the past decade . the authors suggest that the evaluation process should be streamlined and standardized to ensure the validity of the evaluation method . |
Simple and Effective Noisy Channel Modeling for Neural Machine Translation (D19-1)
Copied to clipboard
| Challenge: | Previous work on noisy channel modeling relied on latent variable models that incrementally process the source and target sentence. |
| Approach: | They propose to use a standard sequence to sequence model which utilizes the entire source and target sentences to estimate posterior probability of a target sequence y given a source sequence x. |
| Outcome: | The proposed model outperforms direct models on German-English translations by up to 3.2 BLEU on four language pairs. |
Multilingual k-Nearest-Neighbor Machine Translation (2023.emnlp-main)
Copied to clipboard
| Challenge: | knearest-neighbor machine translation has shown remarkable improvements in machine translation quality by creating a datastore of cached examples. |
| Approach: | They combine k-nearest-neighbor machine translation with a datastore of cached examples to achieve significant improvements in machine translation quality. |
| Outcome: | The proposed approach improves translation quality by 5.3x in multilingual datastores, while limiting performance to low-resource languages. |
SegAugment: Maximizing the Utility of Speech Translation Data with Segmentation-based Augmentations (2023.findings-emnlp)
Copied to clipboard
| Challenge: | End-to-end Speech Translation models are limited by a data bottleneck . end-to end models can address several shortcomings of cascaded models . |
| Approach: | They propose a data augmentation strategy to augment sentence-level datasets by using an Audio Segmentation system to re-segment the speech of each document with different length constraints. |
| Outcome: | The proposed method achieves state-of-the-art results in MuST-C and in mTEDx. |
ConsistTL: Modeling Consistency in Transfer Learning for Low-Resource Neural Machine Translation (2022.emnlp-main)
Copied to clipboard
| Challenge: | Existing transfer learning methods for low-resource NMT are static, which simply transfer knowledge from a parent model to a child model once via parameter initialization. |
| Approach: | They propose a transfer learning method that can continuously transfer knowledge from the parent model during the training of the child model. |
| Outcome: | The proposed method can transfer knowledge from the parent model to the child model during the training of the child. |
Don’t Go Far Off: An Empirical Study on Neural Poetry Translation (2021.emnlp-main)
Copied to clipboard
| Challenge: | despite improvements in machine translation quality, automatic poetry translation remains a challenging problem . et al., a study of automatic poetry translators shows that multilingual fine-tuning on poetic data outperforms bilingual fine-timing on non-poetic text . |
| Approach: | They propose to use poetic parallel corpora for 6 languages to study poetry translation . they find that multilingual fine-tuning on poetic data outperforms bilingual fine-uning . |
| Outcome: | The proposed model outperforms bilingual and multilingual models on poetic data . the proposed model is based on a parallel dataset of poetry translations for several languages . |
Analyzing Multi-Head Self-Attention: Specialized Heads Do the Heavy Lifting, the Rest Can Be Pruned (P19-1)
Copied to clipboard
| Challenge: | et al., 2017) show that multi-head attention is important for neural machine translation. |
| Approach: | They evaluate the contribution made by individual attention heads to the overall performance of the Transformer model and analyze the roles played by them in the encoder. |
| Outcome: | The proposed pruning method removes the vast majority of heads without affecting performance. |
“In-Dialogues We Learn”: Towards Personalized Dialogue Without Pre-defined Profiles through In-Dialogue Learning (2024.emnlp-main)
Copied to clipboard
| Challenge: | Existing approaches to personalized dialogue generate pre-defined profiles that are time-consuming and labor-intensive to create. |
| Approach: | They propose a framework that leverages dialogue history to characterize personas without pre-defined profiles. |
| Outcome: | The proposed framework improves BLEU and ROUGE scores on three datasets and human evaluations further validate the proposed method. |
A Mixture of h - 1 Heads is Better than h Heads (2020.acl-main)
Copied to clipboard
| Challenge: | Evidence has shown that multi-head attentive neural architectures are overparameterized. |
| Approach: | They propose a multi-head attentive neural architecture that “reallocates” attention heads to different inputs. |
| Outcome: | The proposed model outperforms baselines on machine translation and language modeling tasks. |
Towards Automatic Evaluation of Dialog Systems: A Model-Free Off-Policy Evaluation Approach (2021.emnlp-main)
Copied to clipboard
| Challenge: | Existing methods for evaluation of dialog systems are expensive and not scalable . a framework for estimating human evaluation scores is proposed to bridge this gap . |
| Approach: | They propose a framework for estimating human evaluation scores based on off-policy evaluation . they use language quality metrics for single-turn response generation given a fixed context . |
| Outcome: | The proposed framework outperforms existing methods in terms of correlation with human evaluation scores. |
Self-Attention Architectures for Answer-Agnostic Neural Question Generation (P19-1)
Copied to clipboard
| Challenge: | Neural architectures based on self-attention have attracted interest from the research community . a recent study examined the performance of Transformers on a task of Neural Question Generation . |
| Approach: | They propose to adapt Transformers to a task of Neural Question Generation without constraining the model to focus on a specific answer passage. |
| Outcome: | The proposed architectures have obtained significant improvements over the state-of-the-art in several tasks. |
Beyond Shared Vocabulary: Increasing Representational Word Similarities across Languages for Multilingual Machine Translation (2023.emnlp-main)
Copied to clipboard
| Challenge: | Using a shared vocabulary is common practice in multilingual machine translation . however, when words overlap is small, e.g., using different writing systems, knowledge transfer is inhibited . |
| Approach: | They propose a re-parameterized method for building word embeddings using word equivalence classes and graph networks to fuse word embeds across languages. |
| Outcome: | The proposed method achieves evident BLEU improvements on high- and low-resource MNMT scenarios. |
Generating Classical Chinese Poems from Vernacular Chinese (D19-1)
Copied to clipboard
| Challenge: | Existing models for classical Chinese poetry generation only allow users to use keywords to interfere with the meaning of generated poems. |
| Approach: | They propose a model to generate classical Chinese poems from vernacular . their model uses unsupervised machine translation to generate Chinese poems . human evaluation shows it can generate high-quality poems comparable to amateur poems - authors . |
| Outcome: | The proposed model improves the perplexity and BLEU of the proposed model compared with typical models and human evaluation shows it generates high-quality poems comparable to amateur poems. |
Sentence Pair Embeddings Based Evaluation Metric for Abstractive and Extractive Summarization (2022.lrec-1)
Copied to clipboard
| Challenge: | Existing evaluation metrics, such as ROUGE and BLEU, rely on exact word matching and fail to capture semantic similarity. |
| Approach: | They propose to use contextualized word or sentence embeddings to capture semantic similarity between sentences to evaluate text summarization methods. |
| Outcome: | The proposed evaluation metric shows that it performs faster than the current state-of-the-art on the SummEval dataset. |
Multimodal Abstractive Summarization for How2 Videos (P19-1)
Copied to clipboard
| Challenge: | Abstractive summarization is a task of producing a shorter version of the content in the document while preserving its information. |
| Approach: | They propose a new evaluation metric that measures semantic adequacy rather than fluency of abstractive summarization tasks. |
| Outcome: | The proposed model integrates information from different sources into a coherent output. |
Efficient Inference for Multilingual Neural Machine Translation (2021.emnlp-main)
Copied to clipboard
| Challenge: | Multilingual NMT is an attractive solution for production, but to match bilingual quality, it comes at the cost of larger and slower models. |
| Approach: | They propose to use a shallow decoder with vocabulary filtering to speed up inference . they validate their findings with BLEU and chrF on 380 language pairs . |
| Outcome: | The proposed approach can be used in two 20-language multi-parallel settings. |
Unsupervised Domain Clusters in Pretrained Language Models (2020.acl-main)
Copied to clipboard
| Challenge: | Existing methods to select domains from large corpus of data are often over-simplistic and vague. |
| Approach: | They propose to use pre-trained language models to learn sentence representations that cluster by domains without supervision. |
| Outcome: | The proposed methods outperform established methods on domain selection and precision and recall with respect to an oracle selection. |
Using Context in Neural Machine Translation Training Objectives (2020.acl-main)
Copied to clipboard
| Challenge: | Neural Machine Translation (NMT) training is based on document-level metrics, not sentence-level BLEU. |
| Approach: | They propose to merge document-level metrics with batch-level documents to improve NMT training. |
| Outcome: | The proposed training is more robust for document-level metrics than sequence MRT and maximum-likelihood training. |
Neural Machine Translation Methods for Translating Text to Sign Language Glosses (2023.acl-long)
Copied to clipboard
| Challenge: | State-of-the-art techniques common to low resource Machine Translation (MT) are applied to improve MT of spoken language text to Sign Language glosses. |
| Approach: | They propose to use data augmentation, semi-supervised Neural Machine Translation, transfer learning and multilingual NMT to improve MT of spoken language to Sign Language glosses. |
| Outcome: | The proposed models outperform previous work on two German SL corpora and are confirmed by human evaluation. |
Extended Parallel Corpus for Amharic-English Machine Translation (2022.lrec-1)
Copied to clipboard
| Challenge: | Existing approaches to automate the complex task of translation are tedious and expensive. |
| Approach: | They describe acquisition, preprocessing, segmentation, and alignment of an Amharic-English parallel corpus. |
| Outcome: | The proposed corpus outperforms statistical machine translation models by six to seven BLEU points . the results show that the subword models outperformed word-based models by three to four BLUE points compared with the word-base models . |
Evaluating the Knowledge Dependency of Questions (2022.emnlp-main)
Copied to clipboard
Hyeongdon Moon, Yoonseok Yang, Hangyeol Yu, Seunghyun Lee, Myeongho Jeong, Juneyoung Park, Jamin Shin, Minsam Kim, Seungtaek Choi
| Challenge: | Existing evaluation metrics for MCQ generation focus on the n-gram based similarity of the generated MCq to the gold sample and disregard their educational value. |
| Approach: | They propose to use a human survey to measure the MCQ’s answerability given knowledge of the target fact. |
| Outcome: | The proposed methods measure the MCQ’s answerability given knowledge of the target fact. |
CVSS Corpus and Massively Multilingual Speech-to-Speech Translation (2022.lrec-1)
Copied to clipboard
| Challenge: | Existing work on speech-to-speech translation (S2ST) systems rely on text representation, but they are text-centric. |
| Approach: | They introduce a massively multilingual-to-English speech-tospeech translation corpus . they synthesize the translation text from the Common Voice speech corpus and CoVoST 2 into English . |
| Outcome: | The proposed corpus outperforms existing models on CoVoST 2 by 5.8 BLEU . the proposed model outperformed the previous state-of-the-art model without extra data . |
Automatic Gloss-level Data Augmentation for Sign Language Translation (2022.lrec-1)
Copied to clipboard
| Challenge: | Existing methods for enhancing sign language text data are insufficient . fewer studies have been performed on text data augmentation compared to video data . |
| Approach: | They propose three methods to augment sign language text data using Korean sign language gloss dictionary. |
| Outcome: | The proposed method improves translation performance by 0.204 and 0.170 compared to the original data. |
UNION: An Unreferenced Metric for Evaluating Open-ended Story Generation (2020.emnlp-main)
Copied to clipboard
| Challenge: | Existing metrics for open-ended text generation are poorly correlated with human judgments . despite the success of existing metrics, there are few plausible outputs for the same input . |
| Approach: | They propose a UNreferenced measure for evaluating open-ended story generation . it is built on top of BERT and is trained to distinguish human-written stories from negative samples . |
| Outcome: | The proposed measure is more generalizable than state-of-the-art metrics and correlates better with human judgments. |
UniCoRN: Unified Cognitive Signal ReconstructioN bridging cognitive signals and human language (2023.acl-long)
Copied to clipboard
| Challenge: | Existing studies focus on decoding word-level fMRI volumes from a restricted vocabulary. |
| Approach: | They propose an open-vocabulary task to bridge fMRI time series and human language . they use a pre-trained language model to construct a robust encoder for cognitive signals . |
| Outcome: | The proposed task bridges fMRI time series and human language with a baseline model. |
Addressing Posterior Collapse with Mutual Information for Improved Variational Neural Machine Translation (2020.acl-main)
Copied to clipboard
| Challenge: | Existing variational inference models ignore their latent variables, a phenomenon called posterior collapse. |
| Approach: | They propose a new loss function for conditional variational autoencoders that counteracts posterior collapse by using a modified evidence lower bound objective and a factorized decoder. |
| Outcome: | The proposed model yields improved translation quality compared to existing models on WMT RoEn and DeEn. |
ECIS-VQG: Generation of Entity-centric Information-seeking Questions from Videos (2024.emnlp-main)
Copied to clipboard
| Challenge: | Existing studies on question generation from videos are mostly focused on generating questions about common objects and attributes. |
| Approach: | They propose a model architecture combining Transformers, rich context signals and a combination of cross-entropy and contrastive loss function to encourage entity-centric question generation. |
| Outcome: | The proposed system yields BLEU, ROUGE, CIDEr, and METEOR scores of 71.3, 78.6, 7.31, and 81.9. |
Reference-based Metrics Disprove Themselves in Question Generation (2024.findings-emnlp)
Copied to clipboard
| Challenge: | Existing metrics for question generation are based on human-written references . however, the results of the metrics on our study disprove the metrics themselves . |
| Approach: | They propose to use human-written references to evaluate question generation . they propose to combine criteria such as naturalness, answerability, and complexity . |
| Outcome: | The proposed model is based on multi-dimensional criteria such as naturalness, answerability, and complexity, utilizing large language models. |
Neural Machine Translation Quality and Post-Editing Performance (2021.emnlp-main)
Copied to clipboard
| Challenge: | a recent study has shown that MT post-editing can reduce translation quality and speed . a large-scale study involving 30 professional translators examined the relationship between MT performance and post-edited outputs. |
| Approach: | They examine the relationship between MT performance and post-editing time and quality . they use neural MT of high quality to improve translation quality based on phrase-based MT . |
| Outcome: | The proposed model is not stable predictor of time or quality, the authors say . they find that better MT systems lead to fewer changes in the sentences . |
Efficient Domain Adaptation for Non-Autoregressive Machine Translation (2024.findings-acl)
Copied to clipboard
| Challenge: | Existing non-parametric approaches like nearest neighbor machine translation have made small Autoregressive translation models less efficient . despite their impressive generalization and task performance, LLMs suffer from prohibitive inference cost when confronted with specific domains. |
| Approach: | They propose a domain adaptation approach that tailors a k-nearest-neighbor algorithm for NAT models that incorporates the parallel nature of NAT. |
| Outcome: | The proposed approach achieves significant improvements over the Base-NAT model and exhibits enhanced efficiency. |
Is Crowdsourcing Breaking Your Bank? Cost-Effective Fine-Tuning of Pre-trained Language Models with Proximal Policy Optimization (2024.lrec-main)
Copied to clipboard
| Challenge: | Existing methods to improve language models require manual ranking and annotators. |
| Approach: | They propose a self-supervised text ranking approach for applying Proximal-Policy-Optimization to fine-tune language models while eliminating the need for human annotators. |
| Outcome: | The proposed method significantly outperforms baselines regarding BLEU, GLEU, and METEOR scores on three tasks and is consistent with humans. |
Tox-BART: Leveraging Toxicity Attributes for Explanation Generation of Implicit Hate Speech (2024.findings-acl)
Copied to clipboard
| Challenge: | Existing language models to generate implicit hate explanations are lacking in many fields. |
| Approach: | They propose to use language models to generate explicit hate posts to make it clear . they find that simpler models incorporating external toxicity signals outperform KG-infused models . |
| Outcome: | The proposed setup produces more precise explanations than zero-shot GPT-3.5, highlighting the intricate nature of the task. |
KazParC: Kazakh Parallel Corpus for Machine Translation (2024.lrec-main)
Copied to clipboard
| Challenge: | Statistical machine translation gained ground over rule-based machine translation in the late 1990s thanks to its ability to learn from large bilingual corpora. |
| Approach: | They propose to develop a parallel corpus for machine translation across Kazakh, English, Russian, and Turkish. |
| Outcome: | The proposed model outperforms Google Translate and Yandex Translate in terms of performance and evaluation metrics. |
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. |
TLM: Token-Level Masking for Transformers (2023.emnlp-main)
Copied to clipboard
| Challenge: | Structured dropout approaches have been investigated to regularize the multi-head attention mechanism in Transformers. |
| Approach: | They propose a new regularization scheme based on token-level rather than structure-level to reduce overfitting by manipulating the connections between tokens in the multi-head attention via masking. |
| Outcome: | The proposed regularization scheme outperforms attention dropout and DropHead on 18 datasets and can establish a new record on the data-to-text benchmark Rotowire (18.93 BLEU). |
INK: Injecting kNN Knowledge in Nearest Neighbor Machine Translation (2023.acl-long)
Copied to clipboard
| Challenge: | Neural machine translation models induce a non-smooth representation space, which harms its generalization results. |
| Approach: | They propose a framework to smooth the representation space by adjusting neighbor representations with a small number of new parameters. |
| Outcome: | The proposed framework outperforms the state-of-the-art kNN-MT system with average gains of 1.99 COMET and 1.0 BLEU on four benchmark datasets. |
Region-Grounded Report Generation for 3D Medical Imaging: A Fine-Grained Dataset and Graph-Enhanced Framework (2026.acl-long)
Copied to clipboard
Cong Huy Nguyen, Son Dinh Nguyen, Guanlin Li, Tuan Dung Nguyen, Aditya Narayan Sankaran, Mai Huy Thong, Thanh Trung Nguyen, Mai Hong Son, Reza Farahbakhsh, Phi Le Nguyen, Noel Crespi
| Challenge: | Current methods map whole volumes to reports, ignoring the clinical workflow of analyzing localized Regions of Interest (RoIs) Current models exhibit suboptimal accuracy and are prone to significant hallucinations. |
| Approach: | They propose a framework that mimics the professional radiologist diagnostic workflow by employing graph-based relational modules to capture dependencies between RoI attributes. |
| Outcome: | The proposed framework surpasses existing models by 19.7% in BLEU and 4.7% in ROUGE-L while achieving a 45.8% improvement in clinical metrics. |
Hire a Linguist!: Learning Endangered Languages in LLMs with In-Context Linguistic Descriptions (2024.findings-acl)
Copied to clipboard
| Challenge: | Existing LLMs rarely perform well in unseen, endangered languages . Existing models such as Llama and GPT-4 lack a rich corpus of training data . |
| Approach: | They propose a training-free approach to enable an LLM to process unseen languages that hardly occur in its pre-training. |
| Outcome: | The proposed approach elevates translation capability from GPT-4’s 0 to 10.5 BLEU for 10 language directions. |
Evaluating Spatiotemporal Consistency in Automatically Generated Sewing Instructions (2025.emnlp-main)
Copied to clipboard
| Challenge: | Existing methods to generate instructions using large language models require spatiotemporal awareness of multiple objects and their surroundings. |
| Approach: | They propose a tree-based evaluation metric for LLM-generated step-by-step assembly instructions that more accurately reflects spatiotemporal aspects of construction than traditional metrics such as BLEU and BERT similarity scores. |
| Outcome: | The proposed metric better correlates with manually-annotated error counts, and is more robust against artificially-constructed counterfactual examples that are specifically constructed to confound metrics that rely on textual similarity. |
Reinforcement Replaces Supervision: Query focused Summarization using Deep Reinforcement Learning (2023.emnlp-main)
Copied to clipboard
| Challenge: | Query-focused Summarization (QfS) is a system that generates summaries from document(s) based on a query. |
| Approach: | They propose a Query-focused Summarization approach that uses a generalization of Reinforcement Learning (RL) for Natural Language Generation and a better semantic similarity reward. |
| Outcome: | The proposed approach improves on the ROUGE-L metric and in a benchmark dataset. |
MoNMT: Modularly Leveraging Monolingual and Bilingual Knowledge for Neural Machine Translation (2024.lrec-main)
Copied to clipboard
| Challenge: | Existing models for multi-domain translation tasks only use monolingual data, whereas bilingual data is indispensable for improving the models. |
| Approach: | They propose a modular strategy that facilitates the cooperation of monolingual and bilingual knowledge in translation tasks by avoiding catastrophic forgetting. |
| Outcome: | The proposed model exhibits superior generalization and robustness over the conventional approach. |
Extrapolating Multilingual Understanding Models as Multilingual Generators (2023.findings-emnlp)
Copied to clipboard
| Challenge: | Existing multilingual understanding models are not capable of generating high-quality text compared with decoder-based causal language models. |
| Approach: | They propose a method to adapt a multilingual encoder to a language generator with a small number of additional parameters. |
| Outcome: | The proposed approach outperforms initialization-based methods with 9.4 BLEU on machine translation, 8.1 Rouge-L on question generation, and 5.5 METEOR on story generation. |
THOR-MoE: Hierarchical Task-Guided and Context-Responsive Routing for Neural Machine Translation (2025.acl-long)
Copied to clipboard
| Challenge: | Existing sparse Mixture-of-Experts (MoE) solutions may lead to sub-optimal performance . thor-moe uses domain/linguistics-specific knowledge, but lacks context-responsive routing policies . |
| Approach: | They propose a sparse Mixture-of-Experts (MoE) solution which uses task knowledge of NMT into MoE and provides hierarchical task-guided and context-responsive routing policies. |
| Outcome: | thor-MoE can achieve an average improvement of 0.75 BLEU with less than 22% activated parameters on multi-domain translation tasks. |
BiMol-Diff: A Unified Diffusion Framework for Molecular Generation and Captioning (2026.acl-long)
Copied to clipboard
| Challenge: | Autoregressive models struggle with long-range dependencies, while standard diffusion processes apply uniform corruption across positions. |
| Approach: | They propose a framework that bridges molecular structures and natural language . it assigns position-dependent corruption based on token recovery difficulty . |
| Outcome: | The proposed framework improves molecule reconstruction and captioning performance on two datasets. |
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. |
Replace, Paraphrase or Fine-tune? Evaluating Automatic Simplification for Medical Texts in Spanish (2024.lrec-main)
Copied to clipboard
Leonardo Campillos-Llanos, Ana Rosa Terroba, Rocío Bartolomé, Ana Valverde-Mateos, Cristina González, Adrián Capllonch-Carrión, Jonathan Heras
| Challenge: | lexicon-based simplification methods can help patients understand medical documents . but they must ensure that the content is transmitted rigorously and not creating wrong information. |
| Approach: | They tested automatic simplification techniques using a Spanish lexicon of technical and laymen terms. |
| Outcome: | The proposed methods improve the quantitative results and the human evaluation of medical documents. |
VLA-Mark: A cross modal watermark for large vision-language alignment models (2025.emnlp-main)
Copied to clipboard
Shuliang Liu, Zheng Qi, Jesse Jiaxi Xu, Yibo Yan, Junyan Zhang, He Geng, Aiwei Liu, Peijie Jiang, Jia Liu, Yik-Cheung Tam, Xuming Hu
| Challenge: | Existing text watermarking methods disrupt visual-textual alignment, leaving semantic-critical concepts vulnerable. |
| Approach: | They propose a vision-aligned framework that embeds detectable watermarks into outputs . they combine localized patch affinity, global semantic coherence, contextual attention patterns . |
| Outcome: | The proposed framework shows lower PPL and higher BLEU than conventional methods with near-perfect detection (98.8% AUC). |
An Empirical Study of Iterative Refinements for Non-autoregressive Translation (2025.acl-long)
Copied to clipboard
| Challenge: | Iterative non-autoregressive (NAR) models have recently demonstrated impressive performance in varied generation tasks, surpassing the autoregressive Transformer. |
| Approach: | They propose a strategy to conduct efficient refinements without performance declines by using two simple metrics to identify potential problems existing in current refinement processes. |
| Outcome: | The proposed model outperforms the autoregressive Transformer by around one BLEU on average. |
Reasoning While Asking: Transforming Reasoning Large Language Models from Passive Solvers to Proactive Inquirers (2026.acl-long)
Copied to clipboard
| Challenge: | Existing reasoning-oriented LLMs lack a blind self-thinking paradigm . current models fail to recognize when their reasoning is underinformed or based on ambiguous user instructions . |
| Approach: | They propose a new reasoning paradigm that transforms LLMs into proactive inquirers that interleave reasoning with clarification. |
| Outcome: | The proposed model outperforms baseline models on mathematical reasoning, code generation, and document editing. |
HARPO: Hierarchical Agentic Reasoning for User-Aligned Conversational Recommendation (2026.acl-long)
Copied to clipboard
| Challenge: | Recent advances in large language models have significantly improved conversational recommender systems performance. |
| Approach: | They propose a framework that reframes conversational recommendation as a structured decision-making process optimized for multi-dimensional recommendation quality. |
| Outcome: | The proposed framework improves on ReDial, INSPIRED, and MUSE while maintaining competitive response quality. |
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. |
Cross-Examination Framework: A Task-Agnostic Diagnostic for Information Fidelity in Text-to-Text Generation (2026.acl-long)
Copied to clipboard
Tathagata Raha, Clement Christophe, Nada Saadi, Hamza A Javed, Marco AF Pimentel, Ronnie Rajan, Praveenkumar Kanithi
| Challenge: | Traditional metrics like BLEU and BERTScore fail to capture semantic fidelity in generative text-to-text tasks. |
| Approach: | They propose a cross-examination framework that generates verifiable questions from each text and performs a Cross-exam to derive three interpretable scores: Coverage, Conformity, and Consistency. |
| Outcome: | The proposed framework detects critical errors across translation, summarization and clinical note-generation and human expert validation shows it is reliable without gold references. |
Mind the Blind Spots: A Focus-Level Evaluation Framework for LLM Reviews (2025.emnlp-main)
Copied to clipboard
Hyungyu Shin, Jingyu Tang, Yoonjoo Lee, Nayoung Kim, Hyunseung Lim, Ji Yong Cho, Hwajung Hong, Moontae Lee, Juho Kim
| Challenge: | Large Language Models (LLMs) can automatically draft reviews, but determining whether they are trustworthy requires systematic evaluation. |
| Approach: | They propose an automatic focus-level evaluation pipeline based on two sets of facets . authors evaluated LLM reviews at surface-level or content-level . |
| Outcome: | The proposed framework enables automatic evaluation of paper reviews based on two sets of facets . the framework compared open review paper reviews with human experts on validity, clarity, novelty . |
CEBC: Conformal Evidence-Bounded Control for Low-Hallucination Vision–Language Generation (2026.acl-long)
Copied to clipboard
| Challenge: | Existing mitigation approaches reduce hallucinated object mentions at the cost of degraded generation quality or require expensive retraining and task-specific supervision. |
| Approach: | They propose a lightweight framework for low-hallucination vision–language generation . it uses evidence-bounded minimal editing to revise or suppress unsupported referenced entities . |
| Outcome: | The proposed framework reduces hallucinations while maintaining or improving quality metrics. |