MACHINE TRANSLATION

Tulun: Transparent and Adaptable Low-resource Machine Translation (2025.acl-demo)

Challenge:	Existing methods to train machine translation models for low-resource languages are not available.
Approach:	They propose to build a machine translation model for code-switched Kazakh-Russian language pair with no labeled data.
Outcome:	The proposed method beats an existing commercial system by human evaluation on a Kazakh-Russian language pair with no labeled data.

Copied to clipboard

Raphael Merx, Hanna Suominen, Lois Yinghui Hong, Nick Thieberger, Trevor Cohn, Ekaterina Vylomova

The Effects of Language Token Prefixing for Multilingual Machine Translation (2022.aacl-short)

Challenge:	a low-resource language that is the lingua franca in Timor-Leste lacks available corpora in the health domain.
Approach:	They propose a solution that combines neural MT with large language model-based post-editing guided by existing glossaries and translation memories.
Outcome:	The proposed system outperforms both standalone MT and LLM approaches across six low-resource languages on the FLORES dataset.

Copied to clipboard

Rachel Wicks, Kevin Duh

Part Represents Whole: Improving the Evaluation of Machine Translation System Using Entropy Enhanced Metrics (2022.findings-aacl)

Challenge:	In recent years, the field has moved towards large neural models either translating from or into many languages.
Approach:	They propose to prefix language tokens onto a source or target sequence to improve translation performance.
Outcome:	The proposed methods improve translation performance and source side prefixes improve translation.

Copied to clipboard

Yilun Liu, Shimin Tao, Chang Su, Min Zhang, Yanqing Zhao, Hao Yang

TRANSLATIONCORRECT: A Unified Framework for Machine Translation Post-Editing with Predictive Error Assistance (2025.acl-demo)

Challenge:	Existing machine translation metrics have poor correlations with human assessments . entropy-based evaluations are often limited to a limited number of samples .
Approach:	They propose a fast and unsupervised approach to enhance machine translation metrics using entropy by introducing sentence-level difficulty.
Outcome:	The proposed method outperforms existing metrics on five sub-tracks in the WMT19 Metrics shared tasks.

Copied to clipboard

Syed Mekael Wasti, Shou-Yi Hung, Christopher Collins, En-Shiun Annie Lee

Evaluating and Improving the Coreference Capabilities of Machine Translation Models (2023.eacl-main)

Challenge:	Current workflows for machine translation (MT) post-editing and research data collection are inefficient and time-consuming.
Approach:	They propose a framework that combines MT and error prediction within a single environment.
Outcome:	TranslationCorrect exports high-quality span-based annotations in the Error Span Annotation format, using an error taxonomy inspired by Multidimensional Quality Metrics (MQM).

Copied to clipboard

Asaf Yehudai, Arie Cattan, Omri Abend, Gabriel Stanovsky

Cross-lingual Intermediate Fine-tuning improves Dialogue State Tracking (2021.emnlp-main)

Challenge:	Currently, end-to-end models learn coreference resolution implicitly by observing aligned sentences in bilingual corpora.
Approach:	They develop a method that derives coreference clusters from MT output and evaluates them without requiring annotations in the target language.
Outcome:	The proposed model outperforms existing models on three challenging benchmarks.

Copied to clipboard

Nikita Moghe, Mark Steedman, Alexandra Birch

Natural Language Interfaces

Challenge:	Existing methods to make multilingual systems expensive and tedious introduce pipeline of errors.
Approach:	They propose to use pre-trained multilingual models to enhance the transfer learning process by intermediate fine-tuning of pretrained multi-lingual models.
Outcome:	The proposed approach improves on the cross-lingual dialogue state tracking task with only 10% of the target language task data and zero-shot setup respectively.

Few-shot learning through contextual data augmentation (2021.eacl-main)

Copied to clipboard

Farid Arthaud, Rachel Bawden, Alexandra Birch

Low-Resource NLP

Challenge:	Various strategies have been explored to learn from a journalist's post-edits . state-of-the-art APE systems require large numbers of post- edits for training .
Approach:	They propose to teach a pre-trained machine translation model to translate previously unseen words accurately . they extend a data augmentation approach to create training examples with similar contexts .
Outcome:	The proposed model improves accuracy on the scale of one to five examples with only 1 to 5 examples.

Grammatical Error Correction through Round-Trip Machine Translation (2023.findings-eacl)

Copied to clipboard

Yova Kementchedjhieva, Anders Søgaard

Bilingual Sentiment Embeddings: Joint Projection of Sentiment Across Languages (P18-1)

Challenge:	A decade ago the idea of using round-trip MT to guide grammatical error correction was not feasible due to the low quality of MT systems of the day.
Approach:	They propose to use round-trip machine translation to guide grammatical error correction to preserve meaning while mapping its surface form from one language into another.
Outcome:	The proposed system is re-examined across five languages and models of various sizes and yields consistent improvements.

Copied to clipboard

Jeremy Barnes, Roman Klinger, Sabine Schulte im Walde

Unregulated Chinese-to-English Data Expansion Does NOT Work for Neural Event Detection (2022.coling-1)

Challenge:	Existing approaches to sentiment analysis in low-resource languages lack annotated corpora or do not capture sentiment information.
Approach:	They propose a model that represents sentiment in a source and target language without annotated corpus.
Outcome:	The proposed model outperforms state-of-the-art methods on four out of six setups and captures complementary information to machine translation.

Copied to clipboard

Zhongqiu Li, Yu Hong, Jie Wang, Shiming He, Jianmin Yao, Guodong Zhou

Synchronous Refinement for Neural Machine Translation (2022.findings-acl)

Challenge:	Experimental results show that cross-language data expansion results in performance degradation.
Approach:	They leverage cross-language data expansion and retraining to enhance neural Event Detection on English ACE corpus.
Outcome:	The proposed method improves ED performance by 1.6% over the straight data combination.

Copied to clipboard

Kehai Chen, Masao Utiyama, Eiichiro Sumita, Rui Wang, Min Zhang

Language Models

Challenge:	Existing approaches to decode target sentences face a one-pass issue . generated wrong words are added to the historical context to affect the generation of subsequent target words, which hinders the performance of machine translation.
Approach:	They propose a synchronous refinement method to revise potential errors in the generated words by considering part of the target future context.
Outcome:	The proposed method can refine generated target words and generate the next target word synchronously.

SentSim: Crosslingual Semantic Evaluation of Machine Translation (2021.naacl-main)

Copied to clipboard

Yurun Song, Junchen Zhao, Lucia Specia

Unsupervised Neural Machine Translation with Universal Grammar (2021.emnlp-main)

Challenge:	Machine translation (MT) is currently evaluated in one of two ways: monolingually or trained crosslingually by building a supervised model to predict quality scores from human-labeled data.
Approach:	They propose an unsupervised model that directly compares the source and machine translated sentence using strong pretrained multilingual word and sentence representations.
Outcome:	The proposed model outperforms glass-box approaches to quality estimation that rely on a supervised model.

Copied to clipboard

Zuchao Li, Masao Utiyama, Eiichiro Sumita, Hai Zhao

A Natural Diet: Towards Improving Naturalness of Machine Translation Output (2022.findings-acl)

Challenge:	Unsupervised machine translation relies on parallel corpora for training, but performance still lags behind traditional supervised machine translators.
Approach:	They propose to leverage shared grammar clues to provide more explicit language parallel signals to enhance the training of unsupervised machine translation models.
Outcome:	The proposed models improve on a common language pair training task in English and german, and use embedding alignments and pretrained language models to synthesize pseudo parallel corpora.

Copied to clipboard

Markus Freitag, David Vilar, David Grangier, Colin Cherry, George Foster

DecoMT: Decomposed Prompting for Machine Translation Between Related Languages using Large Language Models (2023.emnlp-main)

Challenge:	MT evaluation often focuses on accuracy and fluency without paying much attention to translation style.
Approach:	They propose a method for training machine translation systems to achieve a more natural style by contrasting training data according to the naturalness of the target side.
Outcome:	The proposed method achieves lexical richness on par with human translations, and is preferred by human experts when compared to baseline translations.

Copied to clipboard

Ratish Puduppully, Anoop Kunchukuttan, Raj Dabre, Ai Ti Aw, Nancy Chen

Language Models

Challenge:	Recent work shows the power of few-shot prompting with large language models for tasks like machine translation, summarization, and question answering.
Approach:	They propose a few-shot prompting approach that decomposes the translation process into word chunks.
Outcome:	The proposed approach outperforms established few-shot prompting models with 8 chrF++ scores across languages.

The Interpreter Understands Your Meaning: End-to-end Spoken Language Understanding Aided by Speech Translation (2023.findings-emnlp)

Copied to clipboard

Mutian He, Philip Garner

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

Challenge:	Modern artificial intelligence is characterized by large pretrained language models with strong language capabilities to be adapted to various downstream tasks.
Approach:	They propose to use the task of speech translation (ST) to pretrain speech models for end-to-end SLU on intra- and cross-lingual scenarios.
Outcome:	The proposed model achieves higher performance over baselines on monolingual and multilingual intent classification as well as spoken question answering using SLURP, MINDS-14, and NMSQA benchmarks.

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.

VietMix: A Naturally-Occurring Parallel Corpus and Augmentation Framework for Vietnamese-English Code-Mixed Machine Translation (2026.eacl-long)

Copied to clipboard

Hieu Tran, Phuong-Anh Nguyen-Le, Huy Nghiem, Quang-Nhan Nguyen, Wei Ai, Marine Carpuat

On Creating an English-Thai Code-switched Machine Translation in Medical Domain (2024.findings-emnlp)

Challenge:	Existing approaches to machine translation (MT) systems degrade when faced with code-mixed text.
Approach:	They propose a system that can augment Vietnamese-English code-mixed text with iterative fine-tuning and targeted filtering.
Outcome:	The proposed framework outperforms strong back-translation baselines and improves zero-shot models by up to +11.9 points.

Copied to clipboard

Parinthapat Pengpun, Krittamate Tiankanon, Amrest Chinkamol, Jiramet Kinchagawat, Pitchaya Chairuengjitjaras, Pasit Supholkhan, Pubordee Aussavavirojekul, Chiraphat Boonnag, Kanyakorn Veerakanjana, Hirunkul Phimsiri, Boonthicha Sae-jia, Nattawach Sataudom, Piyalitt Ittichaiwong, Peerat Limkonchotiwat

Selecting Backtranslated Data from Multiple Sources for Improved Neural Machine Translation (2020.acl-main)

Challenge:	despite advances in English-Thai MT, common MT approaches often underperform in the medical field due to their inability to precisely translate medical terminologies.
Approach:	They propose to maintain medical terminology in English within translated text through code-switched translation.
Outcome:	The proposed method shows that medical professionals prefer CS translations that maintain critical English terms accurately, even if it slightly compromises fluency.

Copied to clipboard

Xabier Soto, Dimitar Shterionov, Alberto Poncelas, Andy Way

Jam or Cream First? Modeling Ambiguity in Neural Machine Translation with SCONES (2022.naacl-main)

Challenge:	incorporating backtranslated data from different sources has led to improved results in machine translation (MT)
Approach:	They use a low-resource use-case and a high-resourced language pair to test different backtranslation scenarios and employ data selection to optimise the synthetic corpora.
Outcome:	The proposed method reduces the amount of data used while maintaining high-quality MT systems.

Copied to clipboard

Felix Stahlberg, Shankar Kumar

Lost in Back-Translation: Emotion Preservation in Neural Machine Translation (2020.coling-main)

Challenge:	Existing neural machine translation models learn the probability P (y\|x) of the target sentence given the source sentence x.
Approach:	They propose to replace softmax activation with a multi-label classification layer that can model ambiguity more effectively.
Outcome:	The proposed multi-label classification layer can model ambiguity more effectively . it yields consistent BLEU score gains across six translation directions .

Copied to clipboard

Enrica Troiano, Roman Klinger, Sebastian Padó

Enhancing Taiwanese Hokkien Dual Translation by Exploring and Standardizing of Four Writing Systems (2024.lrec-main)

Challenge:	MT is used to support human-to-human communication across languages, but it is unclear whether it can translate the non-propositional level of emotions.
Approach:	They propose to use a re-ranking approach to change emotions to reverse this tendency . they find that emotions are toned down or amplified through linguistic changes .
Outcome:	The proposed model can be used to change emotions, and it can be applied to other languages.

Copied to clipboard

Bo-Han Lu, Yi-Hsuan Lin, Annie Lee, Richard Tzong-Han Tsai

Phrase-Based & Neural Unsupervised Machine Translation (D18-1)

Challenge:	Currently, machine translation systems cater to high-resource languages (HRLs), while low-resourced languages (LRLs) like Taiwanese Hokkien are relatively under-explored.
Approach:	They propose to use a pre-trained LLaMA 2-7B model specialized in Traditional Mandarin Chinese to leverage orthographic similarities between Taiwanese Hokkien Han and Traditional Mandarin China.
Outcome:	The proposed model bridges the gap between Taiwanese Hokkien and other low-resource languages by using a pre-trained LLaMA 2-7B model and a monolingual corpus.

Copied to clipboard

Guillaume Lample, Myle Ott, Alexis Conneau, Ludovic Denoyer, Marc’Aurelio Ranzato

One Source, Two Targets: Challenges and Rewards of Dual Decoding (2021.emnlp-main)

Challenge:	Recent advances in machine translation have reported near human-level performance on several languages, yet their effectiveness strongly relies on the availability of large amounts of parallel sentences.
Approach:	They propose two models that leverage a careful initialization of the parameters and denoising effect of language models.
Outcome:	The proposed models outperform the current methods on English-French and German-English benchmarks while being simpler and having fewer hyper-parameters.

Copied to clipboard

Jitao Xu, François Yvon

Exploring Document-Level Literary Machine Translation with Parallel Paragraphs from World Literature (2022.emnlp-main)

Challenge:	Neural Machine Translation (NMT) is progressing at a rapid pace.
Approach:	They propose to combine two outputs so that each side depends on the other . they highlight the challenges of dual decoding and analyze the benefits of generating matched, rather than independent, translations.
Outcome:	The proposed system can generate matched, rather than independent, translations.

Copied to clipboard

Katherine Thai, Marzena Karpinska, Kalpesh Krishna, Bill Ray, Moira Inghilleri, John Wieting, Mohit Iyyer

Translationese as a Language in “Multilingual” NMT (2020.acl-main)

Challenge:	Literary translation is a culturally significant task, but it is bottlenecked by the small number of qualified literary translators . a dataset of non-English language novels is used to study literary MT .
Approach:	They use a dataset of non-English language novels aligned to human and automatic English translations to study literary MT.
Outcome:	The proposed model prefers human translations over machine translations at a rate of 84% . state-of-the-art MT metrics do not correlate with preferences, the study finds .

Copied to clipboard

Parker Riley, Isaac Caswell, Markus Freitag, David Grangier

A Survey of Machine Translation Tasks on Nigerian Languages (2022.lrec-1)

Challenge:	Recent work examines the impact of translationese in machine translation evaluation using the WMT evaluation campaign.
Approach:	They propose to use a sentence-level classifier to distinguish translationese from original target text to generate a machine translation model that can produce more natural outputs at test time.
Outcome:	The proposed model produces more natural outputs at test time, yielding gains in human evaluation scores on accuracy and fluency.

Copied to clipboard

Ebelechukwu Nwafor, Anietie Andy

Impacts of Misspelled Queries on Translation and Product Search (2024.acl-long)

Challenge:	Existing work on machine translation of low-resource African languages is limited . despite advances in machine translation, there is limited work on Nigerian languages .
Approach:	They propose to focus on neural machine translation techniques for Nigerian languages . they outline the limitations of machine translation research on the continent .
Outcome:	The proposed research on Nigerian languages highlights the limitations of the current state of the art in machine translation.

Copied to clipboard

Greg Hanneman, Natawut Monaikul, Taichi Nakatani

What is the Best Way for ChatGPT to Translate Poetry? (2024.acl-long)

Challenge:	In end-to-end e-commerce, the inclusion of a dedicated spelling correction model, and the augmentation of that model’s training data with language-relevant phenomena, each improve robustness and consistency of search results.
Approach:	They first analyze the spelling-robustness of a population of machine translation systems and then apply them to a multilingual e-commerce setting to test whether spelling variations affect MT output and user behavior.
Outcome:	The proposed model reduces the number of BPE operations and improves spelling-robustness in six languages.

Copied to clipboard

Shanshan Wang, Derek Wong, Jingming Yao, Lidia Chao

Language Models

Challenge:	Despite promising results, our analysis reveals persistent issues in the translations generated by ChatGPT that warrant attention.
Approach:	They propose an Explanation-Assisted Poetry Machine Translation method which leverages monolingual poetry explanation as a guiding information for the translation process.
Outcome:	The proposed method outperforms traditional translation methods of ChatGPT and the existing online systems in English-Chinese poetry translation.

Improved Pseudo Data for Machine Translation Quality Estimation with Constrained Beam Search (2023.emnlp-main)

Copied to clipboard

Xiang Geng, Yu Zhang, Zhejian Lai, Shuaijie She, Wei Zou, Shimin Tao, Hao Yang, Jiajun Chen, Shujian Huang

Improving Vietnamese-English Medical Machine Translation (2024.lrec-main)

Challenge:	evaluating the quality of machine translation outputs becomes increasingly essential with the rapid development of machine language (MT).
Approach:	They propose to generate pseudo data using the MT model with constrained beam search (CBSQE) they propose to preserve the reference parts with high MT probabilities as correct translations .
Outcome:	The proposed model outperforms strong baselines in both supervised and unsupervised settings.

Copied to clipboard

Nhu Vo, Dat Quoc Nguyen, Dung D. Le, Massimo Piccardi, Wray Buntine

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

Challenge:	Existing high-quality Vietnamese-English parallel datasets are inadequate for translation training.
Approach:	They introduce a high-quality Vietnamese-English parallel dataset for medical translation . they compare Google Translate, ChatGPT, and pre-trained bilingual/multilingual models .
Outcome:	The proposed dataset is compared with translation models from Google Translate and ChatGPT.

Copied to clipboard

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

Multilinguality or Back-translation? A Case Study with Estonian (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

Elizaveta Korotkova, Taido Purason, Agnes Luhtaru, Mark Fishel

Estimating Machine Translation Difficulty (2025.findings-emnlp)

Challenge:	a limited amount of parallel data is available for machine translation, and synthetic data is often used to improve translation quality.
Approach:	They propose a large-scale synthetic corpus of Estonian translations that contains over 1 billion parallel sentences.
Outcome:	The proposed model improves the baseline model while maintaining multilinguality . the proposed model is 6 times larger than the Estonian corpus and twice the size of the Estonial part of the CulturaX corpus.

Copied to clipboard

Lorenzo Proietti, Stefano Perrella, Vilém Zouhar, Roberto Navigli, Tom Kocmi