ENGLISH-GERMAN

Multimodal Neural Machine Translation Using Synthetic Images Transformed by Latent Diffusion Model (2023.acl-srw)

Challenge:	Unsupervised neural machine translation (NMT) is a new approach for machine translation . the model uses only one shared encoder to map pairs of sentences from different languages to a shared-latent space .
Approach:	They propose an unsupervised approach which trains the model without labeling data . they propose two independent encoders but share some partial weights to extract high-level representations of input sentences.
Outcome:	The proposed approach achieves significant improvements on English-German, English-French and Chinese-to-English translation tasks.

Copied to clipboard

Ryoya Yuasa, Akihiro Tamura, Tomoyuki Kajiwara, Takashi Ninomiya, Tsuneo Kato

Analysing the Correlation between Lexical Ambiguity and Translation Quality in a Multimodal Setting using WordNet (2022.naacl-srw)

Challenge:	Existing methods to translate source language sentences using images are not optimal for machine translation.
Approach:	They propose a new multimodal neural machine translation model using synthetic images transformed by a latent diffusion model.
Outcome:	The proposed model improves translation performance on English-German translation tasks using the Multi30k dataset.

Copied to clipboard

Ali Hatami, Paul Buitelaar, Mihael Arcan

Unsupervised Pivot Translation for Distant Languages (P19-1)

Challenge:	Recent studies in machine translation have been focusing on using visual information to improve the translation quality of sentences.
Approach:	They propose to use visual information to improve the output quality of a text-based translation model by extracting ambiguity scores from WordNet.
Outcome:	The proposed model improves translation quality for all sentences in the English-German dataset.

Copied to clipboard

Yichong Leng, Xu Tan, Tao Qin, Xiang-Yang Li, Tie-Yan Liu

EDITOR: An Edit-Based Transformer with Repositioning for Neural Machine Translation with Soft Lexical Constraints (2021.tacl-1)

Challenge:	Unsupervised neural machine translation (NMT) is a popular method for transferring information between languages.
Approach:	They propose an unsupervised pivot translation method which translates a language to a distant language through multiple hops.
Outcome:	The proposed method improves translation on 20 languages and 294 distant languages on 20 different languages and language pairs.

Copied to clipboard

Weijia Xu, Marine Carpuat

OpenKiwi: An Open Source Framework for Quality Estimation (P19-3)

Challenge:	Empirically, EDITOR uses soft lexical constraints more effectively than the Levenshtein Transformer while speeding up decoding dramatically compared to constrained beam search.
Approach:	They propose an Edit-Based TransfOrmer with Repositioning that integrates lexical preferences into output sequences by iterative editing hypotheses.
Outcome:	The proposed model uses soft lexical constraints more effectively than the Levenshtein Transformer while speeding up decoding dramatically compared to constrained beam search.

Copied to clipboard

Fabio Kepler, Jonay Trénous, Marcos Treviso, Miguel Vera, André F. T. Martins

Deep Pivot-Based Modeling for Cross-language Cross-domain Transfer with Minimal Guidance (D18-1)

Challenge:	Existing open-source frameworks for QE are based on complex ensemble systems, complicated architectures, or require not well-documented pretraining and fine-tuning of some components.
Approach:	They introduce OpenKiwi, a Pytorch-based framework for translation quality estimation.
Outcome:	The proposed framework performs state-of-the-art on word-level and sentence-level tasks and is near state-outperforming on sentence- and word-based tasks.

Copied to clipboard

Yftah Ziser, Roi Reichart

Low-Resource NLP

Challenge:	a framework for cross-domain and cross-language transfer has hardly been explored . cross-linguistic and cross language transfer methods are used for multilingual applications .
Approach:	They propose a framework that builds on pivot-based learning, structure-aware Deep Neural Networks and bilingual word embeddings to train a model on labeled data from one language pair.
Outcome:	The proposed model outperforms existing models even when trained in the lazy setup . the proposed model can be applied to nine English-German and nine English - french domain pairs without retraining .

Domain Adaptive Inference for Neural Machine Translation (P19-1)

Copied to clipboard

Danielle Saunders, Felix Stahlberg, Adrià de Gispert, Bill Byrne

TransLLaMa: LLM-based Simultaneous Translation System (2024.findings-emnlp)

Challenge:	Neural Machine Translation models are effective when trained on broad domains with large datasets, such as news translation.
Approach:	They propose a novel approach for adaptive ensemble weighting for Neural Machine Translation by extending Bayesian Interpolation with source information.
Outcome:	The proposed approach improves performance on Spanish-English and English-German tasks without the need for the domain label.

Copied to clipboard

Roman Koshkin, Katsuhito Sudoh, Satoshi Nakamura

Monash University’s Submissions to the WNGT 2019 Document Translation Task (D19-56)

Challenge:	Decoder-only large language models have limited applications in simultaneous machine translation . naively translating each source word immediately results in compromised target quality .
Approach:	a study shows that a pre-trained open-source LLM can control input segmentation directly by generating a special "wait" token.
Outcome:	a new open-source model can control input segmentation directly by generating a special "wait" token.

Copied to clipboard

Sameen Maruf, Gholamreza Haffari

Anchor-based Bilingual Word Embeddings for Low-Resource Languages (2021.acl-short)

Challenge:	Despite the boom of work on document-level machine translation in the past two years, there has been a lack of the application of the proposed approaches to MT shared tasks.
Approach:	They propose to employ an established document-level neural machine translation model for the shared task of Rotowire document translation organised by the 3rd Workshop on Neural Generation and Translation (WNGT 2019).
Outcome:	The proposed model achieves a BLEU score of 39.83 for En-De and 45.06 for De-En translation directions on the Rotowire test set.

Copied to clipboard

Tobias Eder, Viktor Hangya, Alexander Fraser

Representation Learning

Challenge:	Existing approaches to build monolingual word embeddings rely on a cheap bilingual signal and monolingual data.
Approach:	They propose a method where the vector space of the high resource source language is used as a starting point for training an embedding space for the low resource target language.
Outcome:	The proposed approach improves bilingual lexicon induction performance and target language MWE quality.

Document Flattening: Beyond Concatenating Context for Document-Level Neural Machine Translation (2023.eacl-main)

Copied to clipboard

Minghao Wu, George Foster, Lizhen Qu, Gholamreza Haffari

Back-Translation Sampling by Targeting Difficult Words in Neural Machine Translation (D18-1)

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.

Copied to clipboard

Marzieh Fadaee, Christof Monz

Learning to Translate Ambiguous Terminology by Preference Optimization on Post-Edits (2025.emnlp-industry)

Challenge:	Neural machine translation (NMT) uses a sequence-to-sequence model to generate synthetic data.
Approach:	They propose a method that adds synthetic data to sentences with high prediction loss during training and a variety of sampling strategies targeting difficult-to-predict words.
Outcome:	The proposed method improves translation quality by up to 1.7 and 1.2 Bleu points over back-translation using random sampling for German-English and English-German, respectively.

Copied to clipboard

Nathaniel Berger, Johannes Eschbach-Dymanus, Miriam Exel, Matthias Huck, Stefan Riezler

Semi-Autoregressive Neural Machine Translation (D18-1)

Challenge:	Ambiguous terminology can make translation difficult, especially in corporate contexts.
Approach:	They propose to learn how to disambiguate terminology based on human post-edits . they use preference optimization to optimize for correctness using the term post-Edit .
Outcome:	The proposed framework improves term accuracy over a translation oriented LLM without significant losses in COMET score.

Copied to clipboard

Chunqi Wang, Ji Zhang, Haiqing Chen

A Simple and Effective Approach to Coverage-Aware Neural Machine Translation (P18-2)

Challenge:	Existing approaches to neural machine translation are typically autoregressive but suffer from low parallelizability and thus slow at decoding long sequences.
Approach:	They propose a semi-autoregressive Transformer model for fast sequence generation that keeps the autoregressive property in global but relieves in local .
Outcome:	The proposed model achieves 5.58 speedup while maintaining 88% translation quality, significantly better than previous non-autoregressive methods.

Copied to clipboard

Yanyang Li, Tong Xiao, Yinqiao Li, Qiang Wang, Changming Xu, Jingbo Zhu

CTC-based Compression for Direct Speech Translation (2021.eacl-main)

Challenge:	Neural Machine Translation (NMT) models are used to solve translation problems using long-term models.
Approach:	They propose a method to seek a better balance between model confidence and length preference for Neural Machine Translation.
Outcome:	The proposed model improves on Chinese-English and English-German translation tasks.

Copied to clipboard

Marco Gaido, Mauro Cettolo, Matteo Negri, Marco Turchi

Speech & Audio in NLP

Challenge:	Existing studies have shown that a dynamic phone-informed compression of the input audio is beneficial for speech translation (ST).
Approach:	They propose a method which performs a phone-informed compression of the input audio in direct ST models by exploiting the Connectionist Temporal Classification (CTC) they demonstrate that their method brings a 1.3-1.5 BLEU improvement over a strong baseline on two language pairs (English-Italian and English-German)
Outcome:	The proposed method brings a 1.3-1.5 BLEU improvement over a strong baseline on two language pairs (English-Italian and English-German) it reduces memory footprint by more than 10%, and is faster than previous approaches.

Improving Back-Translation with Uncertainty-based Confidence Estimation (D19-1)

Copied to clipboard

Shuo Wang, Yang Liu, Chao Wang, Huanbo Luan, Maosong Sun

Giving the Old a Fresh Spin: Quality Estimation-Assisted Constrained Decoding for Automatic Post-Editing (2025.naacl-short)

Challenge:	Despite the success of low-resource neural machine translation, there is a data scarcity problem in many languages . large-scale, high-quality, and widecoverage bilingual corpora do not exist for most language pairs .
Approach:	They propose to quantify confidence of NMT models based on model uncertainty . they propose to use uncertainty-based confidence measures to improve back-translation .
Outcome:	The proposed model outperforms conventional statistical machine translation (SMT) on Chinese-English and English-German translation tasks.

Copied to clipboard

Sourabh Deoghare, Diptesh Kanojia, Pushpak Bhattacharyya

Iterative Dual Domain Adaptation for Neural Machine Translation (D19-1)

Challenge:	Existing methods to improve automatic post-editing (APE) systems struggle with over-correction, despite the principle of minimal editing.
Approach:	They propose a method that incorporates word-level Quality Estimation (QE) information during the decoding process.
Outcome:	The proposed method improves on English-German, English-Hindi, and English-Marathi language pairs, with TER gains of 0.65, 1.86, and 1.44 points, respectively.

Copied to clipboard

Jiali Zeng, Yang Liu, Jinsong Su, Yubing Ge, Yaojie Lu, Yongjing Yin, Jiebo Luo

Responsible & Trustworthy NLP

Challenge:	Empirical results on Chinese-English and English-German translation tasks demonstrate the effectiveness of our proposed framework.
Approach:	They propose an iterative dual domain adaptation framework for neural machine translation that uses multiple corpora to perform bidirectional translation knowledge transfer.
Outcome:	Empirical results on Chinese-English and English-German translation tasks demonstrate the effectiveness of the proposed framework.

Cross-lingual Annotation Projection in Legal Texts (2020.coling-main)

Copied to clipboard

Andrea Galassi, Kasper Drazewski, Marco Lippi, Paolo Torroni

Generating Diverse Translation from Model Distribution with Dropout (2020.emnlp-main)

Challenge:	a new study examines annotation projection in text classification problems where source documents are published in multiple languages.
Approach:	They propose to use word embeddings and dynamic time warping to create an annotation corpus for text classification problems where source documents are published in multiple languages.
Outcome:	The proposed method is based on word embeddings and dynamic time warping . the aim is to train linguistic tools for the target language without experts .

Copied to clipboard

Xuanfu Wu, Yang Feng, Chenze Shao

Harnessing Multilinguality in Unsupervised Machine Translation for Rare Languages (2021.naacl-main)

Challenge:	Existing neural machine translation models lack diversity in their generation.
Approach:	They propose to generate diverse translations by deriving Bayesian models and sampling models from them for inference.
Outcome:	The proposed method makes a better trade-off between diversity and accuracy.

Copied to clipboard

Xavier Garcia, Aditya Siddhant, Orhan Firat, Ankur Parikh

Quantifying Synthesis and Fusion and their Impact on Machine Translation (2022.naacl-main)

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 .

Copied to clipboard

Arturo Oncevay, Duygu Ataman, Niels Van Berkel, Barry Haddow, Alexandra Birch, Johannes Bjerva

Multilingual and Multimodal Learning for Brazilian Portuguese (2022.lrec-1)

Challenge:	Literature in Natural Language Processing (NLP) typically labels whole language with strict type of morphology, e.g. fusional or agglutinative.
Approach:	They propose to quantify morphological typology at the word and segment level by using two indices: synthesis (e.g. analytic to polysynthetic) and fusion (agglutinative to fusional).
Outcome:	The proposed method reduces the rigidity of NLP classification claims by measuring morphological diversity at the word and segment level.

Copied to clipboard

Júlia Sato, Helena Caseli, Lucia Specia

Quality Estimation-Assisted Automatic Post-Editing (2023.findings-emnlp)

Challenge:	Existing models that learn multimodal and multilingual representations perform better in many natural language tasks.
Approach:	They use a multimodal and multilingual corpus to test its generalization ability for other languages . they achieve a BLEU score of 51.8 and a METEOR score of 78.0 on the test set .
Outcome:	The proposed model outperforms the existing model on a Portuguese-English multimodal translation task.

Copied to clipboard

Sourabh Deoghare, Diptesh Kanojia, Fred Blain, Tharindu Ranasinghe, Pushpak Bhattacharyya

Extract and Edit: An Alternative to Back-Translation for Unsupervised Neural Machine Translation (N19-1)

Challenge:	Existing APE and QE combination strategies have not shown significant performance gains in the field of automatic post-editing (APE).
Approach:	They propose to train a model on APE and QE tasks to improve the APE performance by using a multi-task learning methodology that treats both tasks as a 'bargaining game' they also investigate various existing combination strategies and show that their approach achieves state-of-the-art performance for a ‘distant’ language pair, viz., English-Marathi.
Outcome:	The proposed model improves on two different language pairs, viz., English-Marathi and English-German.

Copied to clipboard

Jiawei Wu, Xin Wang, William Yang Wang

Improving Neural Machine Translation with Conditional Sequence Generative Adversarial Nets (N18-1)

Challenge:	Back-translation has been used in previous approaches for unsupervised neural machine translation, but pseudo sentences are of low quality as translation errors accumulate during training.
Approach:	They propose an approach to extract and edit real sentences from monolingual corpora and introduce a comparative translation loss to evaluate the translated target sentences.
Outcome:	The proposed approach outperforms state-of-the-art translation systems across two benchmarks and two low-resource language pairs by more than 2 BLEU points.

Copied to clipboard

Zhen Yang, Wei Chen, Feng Wang, Bo Xu

SimAlign: High Quality Word Alignments Without Parallel Training Data Using Static and Contextualized Embeddings (2020.findings-emnlp)

Challenge:	Experimental results show that the proposed model consistently outperforms the traditional RNNSearch and the newly emerged state-of-the-art Transformer on English-German and Chinese-English translation tasks.
Approach:	They propose an approach for applying GANs to NMT by building a conditional sequence generative adversarial net with two adversarials.
Outcome:	The proposed model outperforms the existing RNNSearch and Transformer on English-German and Chinese-English translation tasks.

Copied to clipboard

Masoud Jalili Sabet, Philipp Dufter, François Yvon, Hinrich Schütze

Searchable Hidden Intermediates for End-to-End Models of Decomposable Sequence Tasks (2021.naacl-main)

Challenge:	Word alignments are useful for statistical and neural machine translation (NMT) and cross-lingual annotation projection.
Approach:	They propose to leverage multilingual word embeddings for word alignment.
Outcome:	The proposed methods perform better for four languages and comparable for two languages than traditional statistical aligners even with abundant parallel data.

Copied to clipboard

Siddharth Dalmia, Brian Yan, Vikas Raunak, Florian Metze, Shinji Watanabe

Towards Robust Neural Machine Translation (P18-1)

Challenge:	ESPnet framework exploits compositionality to learn searchable hidden representations at intermediate stages of a sequence model using decomposed sub-tasks.
Approach:	They propose a framework that exploits compositionality to learn searchable hidden representations at intermediate stages of a sequence model using decomposed sub-tasks.
Outcome:	The proposed framework outperforms the state-of-the-art on speech translation tasks by +6 and +3 BLEU on the two test sets of Fisher-CallHome and +4 BLUE on the English-German and English-French test sets.

Copied to clipboard

Yong Cheng, Zhaopeng Tu, Fandong Meng, Junjie Zhai, Yang Liu

Thank You, Stingray: Multilingual Large Language Models Can Not (Yet) Disambiguate Cross-Lingual Word Senses (2025.findings-naacl)

Challenge:	Small perturbations in the input can severely distort intermediate representations and thus impact translation quality of neural machine translation models.
Approach:	They propose adversarial stability training to make encoder and decoder robust to perturbations by enabling them to behave similarly for the original input and its perturbed counterpart.
Outcome:	The proposed approach improves translation quality and robustness over strong models on Chinese-English, English-German and English-French translation tasks.

Copied to clipboard

Samuel Cahyawijaya, Ruochen Zhang, Jan Christian Blaise Cruz, Holy Lovenia, Elisa Gilbert, Hiroki Nomoto, Alham Fikri Aji

Semantic Text Processing

Challenge:	Existing studies on multilingual large language models have raised concerns about their reliability beyond English.
Approach:	They propose a benchmark for cross-lingual sense disambiguation that uses false friends to identify the limitation of cross-linguistic sense disembarrassment in LLMs.
Outcome:	The proposed benchmark pinpoints the limitation of cross-lingual sense disambiguation in LLMs by using false friends in four languages.

BiVert: Bidirectional Vocabulary Evaluation Using Relations for Machine Translation (2024.lrec-main)

Copied to clipboard

Carinne Cherf, Yuval Pinter

Guiding Teacher Forcing with Seer Forcing for Neural Machine Translation (2021.acl-long)

Challenge:	Neural machine translation (NMT) evaluation is crucial to determine the quality of translations.
Approach:	They propose a bidirectional semantic-based evaluation method to assess the sense distance of the translation from the source text.
Outcome:	The proposed method uses the multilingual encyclopedic dictionary BabelNet . it shows a strong correlation between the evaluation scores and human assessments .

Copied to clipboard

Yang Feng, Shuhao Gu, Dengji Guo, Zhengxin Yang, Chenze Shao

Cascade versus Direct Speech Translation: Do the Differences Still Make a Difference? (2021.acl-long)

Challenge:	Neural machine translation models are usually based on attention-based encoder-decoder frameworks.
Approach:	They introduce a seer decoder into the encoder-decoder framework during training . they force the conventional decoded decodes to simulate the behavior of the seer .
Outcome:	The proposed method outperforms baselines on Chinese, English and German translation tasks.

Copied to clipboard

Luisa Bentivogli, Mauro Cettolo, Marco Gaido, Alina Karakanta, Alberto Martinelli, Matteo Negri, Marco Turchi

Progressive Multi-Granularity Training for Non-Autoregressive Translation (2021.findings-acl)

Challenge:	a gap between direct approaches to speech translation (ST) and traditional cascade solutions has gradually decreased . a recent study found that the subtle differences observed in their behavior are not sufficient for humans neither to distinguish them nor to prefer one over the other.
Approach:	They compare state-of-the-art systems representative of the two paradigms . they find subtle differences observed in their behavior are not sufficient .
Outcome:	The proposed system is compared with state-of-the-art systems representative of the two paradigms.

Copied to clipboard

Liang Ding, Longyue Wang, Xuebo Liu, Derek F. Wong, Dacheng Tao, Zhaopeng Tu

Guiding Large Language Models to Post-Edit Machine Translation with Error Annotations (2024.findings-naacl)

Challenge:	Non-autoregressive translation models are weak at learning high-mode knowledge, argues a new study . despite the improved learning difficulty, there are still complicated word orders and structures in the synthetic sentences, making the NAT performance sub-optimal.
Approach:	They propose to train non-autoregressive translation models to learn fine-grained lower-mode knowledge . they break down sentence-level examples into three types and increase granularities .
Outcome:	The proposed method improves phrase translation accuracy and model reordering ability against strong NAT baselines.

Copied to clipboard

Dayeon Ki, Marine Carpuat

Visual Cues and Error Correction for Translation Robustness (2021.findings-emnlp)

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.

Copied to clipboard

Zhenhao Li, Marek Rei, Lucia Specia

Reference Network for Neural Machine Translation (P19-1)

Challenge:	Existing robustness techniques fail when faced with unseen types of noise and their performance degrades on clean texts.
Approach:	They propose visual context to improve translation robustness for noisy texts . they also propose an error correction training regime that can be used as an auxiliary task .
Outcome:	The proposed training regime improves translation robustness on noisy texts while maintaining translation quality on clean texts.

Copied to clipboard

Han Fu, Chenghao Liu, Jianling Sun

Look Harder: A Neural Machine Translation Model with Hard Attention (P19-1)

Challenge:	Neural Machine Translation (NMT) generates translations in isolation, resulting in translation inconsistency and ambiguity.
Approach:	They propose to incorporate referring process into translation decoding of NMT by using local coordinates coding to obtain global context vectors containing monolingual and bilingual contextual information.
Outcome:	The proposed model improves translation quality with lightweight computation cost on Chinese-English and English-German translation tasks.

Copied to clipboard

Sathish Reddy Indurthi, Insoo Chung, Sangha Kim

Scheduled Multi-task Learning for Neural Chat Translation (2022.acl-long)

Challenge:	Soft-attention based Neural Machine Translation models attend all the words in the source sequence for each target token, which makes them ineffective for long sequence translation.
Approach:	They propose a hard-attention based NMT model which selects a subset of source tokens for each target token to effectively handle long sequence translation.
Outcome:	The proposed model performs better on long sequences and achieves significant improvement on English-German and English-French translation tasks compared to soft-attention based models.

Copied to clipboard

Yunlong Liang, Fandong Meng, Jinan Xu, Yufeng Chen, Jie Zhou

Margin-based Parallel Corpus Mining with Multilingual Sentence Embeddings (P19-1)

Challenge:	Existing methods to improve chat translation focus on modeling bilingual dialogue characteristics . however, there is insufficient data and simple joint training methods .
Approach:	They propose a scheduled multi-task learning framework to incorporate large-scale chat translation data into training by adding a second pre-training stage between the original pre- training and fine-tuning stages.
Outcome:	The proposed framework improves translation tasks on four language directions.

Copied to clipboard

Mikel Artetxe, Holger Schwenk

Representation Learning

Challenge:	Traditional parallel corpus mining methods focus on the textual content instead of the size and quality of training data.
Approach:	They propose a method for machine translation based on multilingual sentence embeddings.
Outcome:	The proposed method outperforms the best published methods on the BUCC mining task and the UN reconstruction task by more than 10 F1 and 30 precision points.

Selective Attention for Context-aware Neural Machine Translation (N19-1)

Copied to clipboard

Sameen Maruf, André F. T. Martins, Gholamreza Haffari

Lexically Constrained Neural Machine Translation with Levenshtein Transformer (2020.acl-main)

Challenge:	Recent work in context-aware NMT considers only a few previous sentences as context . current systems fail to achieve fluent, good quality translation for a full document .
Approach:	They propose a top-down approach to hierarchical attention for context-aware NMT which uses sparse attention to selectively focus on relevant sentences in the document context.
Outcome:	The proposed approach outperforms context-agnostic baselines and context-based baselines on English-German datasets.

Copied to clipboard

Raymond Hendy Susanto, Shamil Chollampatt, Liling Tan

Fixing Translation Divergences in Parallel Corpora for Neural MT (D18-1)

Challenge:	Existing approaches to incorporate lexical constraints in neural machine translation have been unsuccessful .
Approach:	They propose an algorithm that incorporates lexical constraints into neural machine translation.
Outcome:	The proposed method improves on English-German datasets without modification . it does not require any modification to the training procedure and can be easily applied at runtime with custom dictionaries.

Copied to clipboard

MinhQuang Pham, Josep Crego, Jean Senellart, François Yvon

Understanding and Improving the Robustness of Terminology Constraints in Neural Machine Translation (2023.acl-long)

Challenge:	Existing methods to detect translation divergences from parallel corpora are noisy and limited in size.
Approach:	They propose an unsupervised method for detecting translation divergences in parallel sentences . they use a neural network that computes cross-lingual sentence similarity scores .
Outcome:	The proposed method improves translation performance for English-French and English-German translation tasks.

Copied to clipboard

Huaao Zhang, Qiang Wang, Bo Qin, Zelin Shi, Haibo Wang, Ming Chen

Improving Neural Machine Translation by Multi-Knowledge Integration with Prompting (2023.findings-emnlp)

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.

Copied to clipboard

Ke Wang, Jun Xie, Yuqi Zhang, Yu Zhao

End-to-End Non-Autoregressive Neural Machine Translation with Connectionist Temporal Classification (D18-1)

Challenge:	Existing methods focus on how to integrate multiple types of knowledge into NMT models .
Approach:	They propose a framework that integrates multiple types of knowledge into NMT models . they use multiple types as prefix-prompts of input for the encoder and decoder .
Outcome:	The proposed framework outperforms baselines on English-Chinese and English-German translation.

Copied to clipboard

Jindřich Libovický, Jindřich Helcl

Information Retrieval

Challenge:	Autoregressive decoding is the only part of sequence-to-sequence models that prevents massive parallelization at inference time.
Approach:	They propose a non-autoregressive architecture based on connectionist temporal classification . they conduct experiments on the WMT English-Romanian and English-German datasets .
Outcome:	The proposed model achieves a significant speedup over autoregressive models . the model can be trained end-to-end and maintains translation quality comparable to other models compared to autoregression models based on connectionist temporal classification .

Refer to the Reference: Reference-focused Synthetic Automatic Post-Editing Data Generation (2025.coling-main)

Copied to clipboard

Sourabh Dattatray Deoghare, Diptesh Kanojia, Pushpak Bhattacharyya

SimulSpeech: End-to-End Simultaneous Speech to Text Translation (2020.acl-main)

Challenge:	Existing approaches to synthetic APE data generation use source (src) sentences in a parallel corpus to obtain translations (mt) through an MT system and treat corresponding reference (ref) sentences as post-edits (pe).
Approach:	They propose a reference-focused synthetic APE data generation technique that uses ‘ref’ instead of src’ sentences to obtain corrupted translations.
Outcome:	The proposed technique improves on English-German, English-Russian, English -Marathi, English and Hindi language pairs.

Copied to clipboard

Yi Ren, Jinglin Liu, Xu Tan, Chen Zhang, Tao Qin, Zhou Zhao, Tie-Yan Liu

MultiMWE: Building a Multi-lingual Multi-Word Expression (MWE) Parallel Corpora (2020.lrec-1)

Challenge:	SimulSpeech is an end-to-end simultaneous speech to text translation system . conventional approaches to simultaneous speech translation divide the translation process into two stages .
Approach:	They develop an end-to-end simultaneous speech to text translation system which translates speech in source language to text in target language concurrently.
Outcome:	The proposed system achieves reasonable BLEU scores and lower delay compared to full-sentence translation model.

Copied to clipboard

Lifeng Han, Gareth Jones, Alan Smeaton

Supervised Visual Attention for Multimodal Neural Machine Translation (2020.coling-main)

Challenge:	Existing bilingual or multi-lingual MWE corpora are limited for multilingual use . only 871 pairs of English-German MWEs are available for research .
Approach:	They present a collection of bilingual and multi-lingual MWEs extracted from parallel corpora.
Outcome:	The available bilingual or multi-lingual MWE corpus is very limited . the collection is a small collection of 871 pairs of English-German MWEs .

Copied to clipboard

Tetsuro Nishihara, Akihiro Tamura, Takashi Ninomiya, Yutaro Omote, Hideki Nakayama

FooTweets: A Bilingual Parallel Corpus of World Cup Tweets (L18-1)

Challenge:	Existing studies show that a conventional visual attention mechanism trained in an unsupervised manner is not effective for multimodal neural machine translation.
Approach:	They propose a supervised visual attention mechanism for multimodal neural machine translation that captures the relationship between a word and an image region more precisely than a conventional visual attention system.
Outcome:	The proposed model improves on English-German and German-English translation tasks and English-Japanese and Japanese-English tasks using the Flickr30k Entities JP dataset.

Copied to clipboard

Henny Sluyter-Gäthje, Pintu Lohar, Haithem Afli, Andy Way

Robust Neural Machine Translation with Doubly Adversarial Inputs (P19-1)

Challenge:	a new study analyzes the nature of twitter data and compares it with other social networking websites.
Approach:	They develop a parallel corpus of tweets for an English-German pair that can be translated into German using a machine translation tool.
Outcome:	The proposed method can be used to translate tweets from English to German using a parallel corpus of 4, 000 tweets.

Copied to clipboard

Yong Cheng, Lu Jiang, Wolfgang Macherey

Robustness in NLP

Challenge:	Neural machine translation (NMT) models suffer from noisy perturbations in the input . a gradient-based method to craft adversarial examples informed by the translation loss is proposed .
Approach:	They propose an approach to improve the robustness of NMT models by attacking the translation model with adversarial source examples and defending the model with a target input.
Outcome:	The proposed approach improves translation performance and robustness on clean inputs and higher on noisy data.

Online Versus Offline NMT Quality: An In-depth Analysis on English-German and German-English (2020.coling-main)

Copied to clipboard

Maha Elbayad, Michael Ustaszewski, Emmanuelle Esperança-Rodier, Francis Brunet-Manquat, Jakob Verbeek, Laurent Besacier

Simplifying Neural Machine Translation with Addition-Subtraction Twin-Gated Recurrent Networks (D18-1)

Challenge:	Existing studies compare offline and online neural machine translation architectures . we examine the impact of online decoding constraints on the translation quality .
Approach:	They evaluate offline and online neural machine translation architectures using human evaluations on English-German and German-English language pairs.
Outcome:	The proposed models are particularly sensitive to latency constraints and are well-suited for offline translation tasks.

Copied to clipboard

Biao Zhang, Deyi Xiong, Jinsong Su, Qian Lin, Huiji Zhang

Improving Both Domain Robustness and Domain Adaptability in Machine Translation (2022.coling-1)

Challenge:	Existing gated recurrent networks have a vanishing gradient, allowing for more matrix transformations and less transparent functions.
Approach:	They propose an additionsubtraction twin-gated recurrent network (ATR) to simplify neural machine translation.
Outcome:	The proposed system is more transparent than LSTM/GRU due to the simplification.

Copied to clipboard

Wen Lai, Jindřich Libovický, Alexander Fraser

Responsible & Trustworthy NLP

Challenge:	Existing approaches to domain adaptation for NMT depend on high-quality parallel data.
Approach:	They propose a meta-learning framework which improves domain robustness and adaptability . they use a word-level domain mixing model and a domain classifier to integrate it .
Outcome:	The proposed approach improves domain robustness and adaptability in seen and unseen domains.

Modeling Localness for Self-Attention Networks (D18-1)

Copied to clipboard

Baosong Yang, Zhaopeng Tu, Derek F. Wong, Fandong Meng, Lidia S. Chao, Tong Zhang

Semantic Text Processing

Challenge:	Existing approaches to model locality for self-attention networks have shown great value for capturing global dependencies.
Approach:	They propose to model localness for self-attention networks to capture local context . they cast localness modeling as a learnable Gaussian bias, which indicates the central and scope of the local region to be paid more attention.
Outcome:	The proposed model improves the ability to capture local context and improves accuracy.

Rule-based Morphological Inflection Improves Neural Terminology Translation (2021.emnlp-main)

Copied to clipboard

Weijia Xu, Marine Carpuat

CCMatrix: Mining Billions of High-Quality Parallel Sentences on the Web (2021.acl-long)

Challenge:	Current approaches to incorporating terminology constraints in machine translation (MT) typically assume that the constraint terms are provided in their correct morphological forms.
Approach:	They propose a framework for incorporating lemma constraints in machine translation . they use a cross-lingual inflection module that inflects the target lemmo constraints based on the source context.
Outcome:	The proposed framework outperforms existing methods with lower training costs and linguistic knowledge in domain adaptation and low-resource MT settings.

Copied to clipboard

Holger Schwenk, Guillaume Wenzek, Sergey Edunov, Edouard Grave, Armand Joulin, Angela Fan

AdvAug: Robust Adversarial Augmentation for Neural Machine Translation (2020.acl-main)

Challenge:	Using a curated common crawl corpus, we were able to mine 10.8 billion parallel sentences out of which only 2.9 billions are aligned with English.
Approach:	They use 32 snapshots of a curated common crawl corpus totaling 71 billion unique sentences to mine 10.8 billion parallel sentences out of which only 2.9 billions are aligned with English.
Outcome:	The proposed system outperforms the best single systems on the WMT’19 test set for English-German/Russian/Chinese and outperformed the best submission at the 2020 WAT workshop.

Copied to clipboard

Yong Cheng, Lu Jiang, Wolfgang Macherey, Jacob Eisenstein

Robustness in NLP

Challenge:	Recent work in neural machine translation has led to dramatic improvements in both research and commercial systems.
Approach:	They propose a adversarial augmentation method for Neural Machine Translation that minimizes vicinal risk over virtual sentences . they use a novel vicinity distribution for adversarials to describe a smooth interpolated embedding space .
Outcome:	The proposed method outperforms the current method on Chinese-English, English-French, and English-German translation benchmarks.

Learning Adaptive Segmentation Policy for End-to-End Simultaneous Translation (2022.acl-long)

Copied to clipboard

Ruiqing Zhang, Zhongjun He, Hua Wu, Haifeng Wang

Speech & Audio in NLP

Challenge:	Existing methods to perform simultaneous speech-to-text translation ignore contextual information and suffer from low translation quality.
Approach:	They propose an adaptive segmentation policy for simultaneous speech-to-text translation . it learns to segment the source streaming speech into meaningful units .
Outcome:	The proposed method achieves a good accuracy-latency trade-off over state-of-the-art methods on English-German and Chinese-English.

CLAD-ST: Contrastive Learning with Adversarial Data for Robust Speech Translation (2023.emnlp-main)

Copied to clipboard

Sathish Indurthi, Shamil Chollampatt, Ravi Agrawal, Marco Turchi

Critical Learning Periods: Leveraging Early Training Dynamics for Efficient Data Pruning (2024.findings-acl)

Challenge:	Cascaded approach is the most popular choice for speech translation, but lacks robustness when dealing with noisy inputs.
Approach:	They propose a cascaded approach that uses an automatic speech recognition model and a machine translation model to translate speech in one language to text in another language.
Outcome:	The proposed approach achieves significant gains of up to 3 BLEU scores in English-German and English-French speech translation without hurting the translation quality on clean text.

Copied to clipboard

Everlyn Chimoto, Jay Gala, Orevaoghene Ahia, Julia Kreutzer, Bruce Bassett, Sara Hooker

Vocabulary Learning via Optimal Transport for Neural Machine Translation (2021.acl-long)

Challenge:	Neural Machine Translation models are extremely data-hungry and require a large dataset to maintain data quality.
Approach:	They propose a new data pruning technique that leverages early model training dynamics to identify the most relevant data points for model performance.
Outcome:	The proposed technique outperforms the benchmarks on indo-European languages while pruning up to 50% of training data.

Copied to clipboard

Jingjing Xu, Hao Zhou, Chun Gan, Zaixiang Zheng, Lei Li

Uncertainty-Aware Balancing for Multilingual and Multi-Domain Neural Machine Translation Training (2021.emnlp-main)

Challenge:	Empirical results show that VOLT beats widely-used vocabularies in diverse scenarios, including WMT-14 English-German translation, TED bilingual translation, and TED multilingual translation.
Approach:	They propose a token dictionary solution that can be used without trial training to find the best dictionary with a proper size.
Outcome:	The proposed solution beats widely-used vocabularies in English-German translation, TED bilingual translation, and TED multilingual translation.

Copied to clipboard

Minghao Wu, Yitong Li, Meng Zhang, Liangyou Li, Gholamreza Haffari, Qun Liu

Redefining Machine Simultaneous Interpretation: From Incremental Translation to Human-Like Strategies (2026.findings-acl)

Challenge:	MultiUAT dynamically adjusts training data usage based on model’s uncertainty on a small set of trusted clean data for multi-corpus machine translation.
Approach:	They propose an approach that dynamically adjusts the training data usage based on the model’s uncertainty on a small set of trusted clean data for multi-corpus machine translation.
Outcome:	The proposed approach outperforms baselines on 16 languages and 2 domains on English-German translation.

Copied to clipboard

Qianen Zhang, Zeyu Yang, Satoshi Nakamura

DictDis: Dictionary Constrained Disambiguation for Improved NMT (2024.findings-emnlp)

Challenge:	Simultaneous machine translation requires high-quality translations under strict real-time constraints.
Approach:	They extend the action space of simultaneous machine translation with four adaptive actions . they adapt these actions in a large language model framework and construct training references .
Outcome:	The proposed framework improves semantic metrics and achieves lower delay compared to reference translations and salami-based baselines.

Copied to clipboard

Ayush Maheshwari, Preethi Jyothi, Ganesh Ramakrishnan

JParaCrawl v3.0: A Large-scale English-Japanese Parallel Corpus (2022.lrec-1)

Challenge:	Existing approaches to domain-specific neural machine translation (NMT) are lexically constrained and draw from domain- specific dictionaries.
Approach:	They propose a lexically constrained neural machine translation system that disambiguates between multiple dictionary candidates.
Outcome:	The proposed system disambiguates between multiple candidate translations derived from dictionaries on English-Hindi, English-German, and English-French datasets.

Copied to clipboard

Makoto Morishita, Katsuki Chousa, Jun Suzuki, Masaaki Nagata

Leveraging GPT-4 for Automatic Translation Post-Editing (2023.findings-emnlp)

Challenge:	Existing parallel corpora for English-Japanese are limited, limiting the accuracy of machine translation models.
Approach:	They propose a web-based English-Japanese parallel corpus with 21 million unique sentence pairs . this is more than twice as many as the previous corpus JParaCrawl v2.0 .
Outcome:	The proposed corpus boosts the accuracy of machine translation models on various domains.

Copied to clipboard

Vikas Raunak, Amr Sharaf, Yiren Wang, Hany Awadalla, Arul Menezes

Glitter: A Multi-Sentence, Multi-Reference Benchmark for Gender-Fair German Machine Translation (2025.findings-emnlp)

Challenge:	Neural Machine Translation models still require translation post-editing to rectify errors and enhance quality under critical settings.
Approach:	They use GPT-4 to automatically post-edit NMT outputs across several language pairs . they show that GPT4 is adept at translation post- editing, producing meaningful edits .
Outcome:	The proposed translation post-editor improves on state-of-the-art language models on English-Chinese, English-German, Chinese-English and German-English language pairs.

Copied to clipboard

A Pranav, Janiça Hackenbuchner, Giuseppe Attanasio, Manuel Lardelli, Anne Lauscher

SpeechAlign: A Framework for Speech Translation Alignment Evaluation (2024.lrec-main)

Challenge:	Existing MT models are limited in size and often consist of single sentences or single gender-fair formulation types.
Approach:	They propose a benchmark for machine translation that features extended passages with professional translations implementing gender-fair alternatives: neutral rewording, typographical solutions and neologistic forms.
Outcome:	The proposed benchmark features extended passages with professional translations implementing three gender-fair alternatives: neutral rewording, typographical solutions (gender star), and neologistic forms (-ens forms).

Copied to clipboard

Belen Alastruey, Aleix Sant, Gerard I. Gállego, David Dale, Marta R. Costa-jussà