Machine Translation

Also known as MT

Overview

Machine translation studies how to produce useful translations across languages, including low-resource languages, specialized domains, dialects, and long or multimodal content. Common approaches include Transformer-based neural systems and large language models, adapted with parallel or synthetic data, retrieval, preference optimization, and reinforcement learning; speech and image translation also combine language models with audio or visual information. Evaluation uses automatic metrics and human review, with newer benchmarks testing terminology, context, cultural meaning, style, bias, and instruction following. A central tension is that gains on standard scores do not always mean translations are faithful or appropriate, while broad language coverage, low latency, privacy, and limited data remain practical challenges.

Latest papers

CardsList

283 papers34 papers in the last four weeks, level with the four weeks before. 0.2% of all new papers.

  1. Does Machine Translation Retain Media Bias?

    Oct 14, 2026Silvia V. Gargova, Tim Menzner, Jochen L. LeidnerMachine TranslationMT Evaluation

  2. SIREN: Situation-aware Index for Response and Emergency ActioNability in Crisis Translation

    Oct 12, 2026Maria Carmen Staiano, Lifeng Han, Johanna Monti +1Machine TranslationMT Evaluation

  3. PATMT2: Two-stage domain adaptation for multilingual patent translation

    Oct 12, 2026Xiaowei Su, Xusen ChengMachine Translation

  4. HexaBee-4B: Six-Language Translation with Multilingual Answering and Bidirectional Supervision

    Oct 12, 2026Iman Barati, Mohammadmostafa Rostamkhani, Mohammad BadzohrehMachine TranslationMultilingual Language Models

  5. bharatSetu: a 1M x 22 bridge for indic translation

    Oct 11, 2026Haq Nawaz Malik, Nahfid Nissar, Faizan IqbalLow-Resource MTMachine Translation

  6. Feedback as an Interface: Controlling Form and Detail in LLM Translation Refinement

    Oct 11, 2026Yiqi Liu, Flavjo Tomori, Nafise Sadat Moosavi +2Machine Translation

  7. Who Receives Respect? A Counterfactual Benchmark for Honorific Allocation Bias in Bengali

    Oct 10, 2026Ajwad Abrar, Md Kamrul Hasan, Hasan MahmudLanguage Model Bias EvaluationDemographic Bias in Language Models

  8. The Constitution Speaks Nheengatu: An Open MT System and Reproducible Corpus Pipeline for the Amazonian Língua Geral

    Oct 10, 2026Fabrício Carraro, Rodolfo Joel Zevallos, Rodrigo Gonçalves de Souza +2Machine TranslationLow-Resource MT

  9. Fact over Fiction: Detection of Pathological Hallucinations in Sinhala-to-English Neural Machine Translation

    Oct 8, 2026Navam Obeysekara, Nevidu JayatillekeHallucination DetectionHallucination in Language Models

  10. Generative AI translations in high-stakes emergency messaging

    Oct 6, 2026Nune Ayvazan, Anthony Pym, Yu HaoDisaster ResponseMachine Translation

  11. Quality-Aware Self-Correcting Speech Translation on an Edge Device

    Oct 6, 2026Zubair Ajmal Farooq, Diptesh KanojiaSpeech TranslationMachine Translation

  12. Investigating Model Compression for Neural Machine Translation in the Biomedical Domain

    Oct 4, 2026Maria Zafar, Souhail Bakkali, Rejwanul HaqueModel CompressionMachine Translation

  13. ReSCUE: Re-translation with Sentence Commitment for Unsegmented Long-Form Simultaneous Sign Language Translation

    Oct 2, 2026Sihan Ren, Gaozheng Li, Yuanshang Quan +5Sign Language TranslationMachine Translation

  14. "I just assumed that it would translate": examining MT risk awareness among healthcare staff with abbreviations as a use case

    Oct 1, 2026Eleanor Taylor-Stilgoe, Félix do Carmo, Constantin OrăsanMachine TranslationHealthcare

  15. Precision over Scale: A Polish-Silesian Benchmark and a Translation System Outperforming Open-Source and Commercial Models

    Oct 1, 2026Grzegorz Kulik, Mikołaj Pokrywka, Adam Jatowt +1Low-Resource MTDialectal MT

  16. Breaking Babel: A Self-Evolving Multi-Agent System for Long-Form Subtitle Translation

    Sep 29, 2026Haibo Jin, Xinjie Li, Najmeh Sadoughi +4Multi-Agent LLM SystemsDocument-Level MT

  17. Dual-Stream Simultaneous Translation via 2D Grid Attention

    Sep 28, 2026Yu Pu, Wei-Qiang ZhangTransformer AttentionAttention Mechanisms

  18. Reference-Grounded Data Curation for Instruction-Following Thai-English Machine Translation

    Sep 28, 2026Thodsaporn Chay-intr, Krittapad Harnchang, Mahannop Thabua +2Training Data CurationMachine Translation

  19. BaatCheet: A Multilingual Corpus for Dialogue Translation in Indian Languages

    Sep 27, 2026Priyanka Dasari, Yuvrajsinh D. Bodana, Vandan Mujadia +3Machine Translation

  20. Improving Visual Sensitivity of LLMs on Multimodal Machine Translation with Metric-based Loss Weighting

    Sep 25, 2026Paweł Mąka, Piotr Andruszkiewicz, Yusuf Can Semerci +2Multimodal MTMachine Translation

  21. TTLab at AlexandriaX-2026: A Fine-Tuned Surface Tagger for Arabic Machine-Translation Error-Span Detection and Classification

    Sep 24, 2026Ali Abusaleh, Bhuvanesh Verma, Alexander MehlerArabic NLPMachine Translation

  22. Tag-Aware Structured Text Translation: Towards a Systematic Understanding

    Sep 24, 2026Zhanglin Wu, Hengchao Shang, Daimeng Wei +5Multi-Objective Language Model AlignmentMachine Translation

  23. COILD: An Indic-Centric Parallel Corpus and Benchmark for Machine Translation Across Indian Languages

    Sep 23, 2026Kshetrimayum Boynao Singh, Nitin Kumar Mishra, Palash Pratim Dutta +22Low-Resource MTMachine Translation

  24. Fine-Tuning LLMs for Translation: General Forgetting Mitigation Does Not Preserve MT-Specific Instruction Following

    Sep 23, 2026Niklas Scholz, David Thulke, Abdallah Nasir +3LLM Fine-TuningElastic Weight Consolidation

  25. Scaling Attention Head Analysis via Gradient-Based Attribution in Context-Aware Machine Translation

    Sep 23, 2026Paweł Mąka, Yusuf Can Semerci, Jan Scholtes +1Gradient-Based AttributionAttention Head Analysis

  26. AlexandriaX 2026: The First Shared Task on Dialectal Arabic Machine Translation

    Sep 19, 2026Abdellah El Mekki, AbdelRahim A. Elmadany, Samar M. Magdy +6Context-Aware MTDialectal MT