Context-Aware MT

MT: Machine Translation

Follow this topic Ask about this topic

Latest papers

12 papers3 papers in the last four weeks, level with the four weeks before. 0.0% of all new papers.

Training with Ciphers to Enhance In-Context Terminology Learning For Translation from Rare Languages
Oct 17, 2026Deevyanshu Malu, Deeptanshu Malu, Sunita SarawagiMachine Translation In-Context Learning
IIT Bombay
alkhder at AlexandriaX-2026: Context-Aware English-to-Dialectal Arabic Dialogue Translation with QLoRA-Fine-Tuned NileChat-3B
Oct 15, 2026Hasan Alkhder, Maher Pasa, Maria Hanini +2Machine Translation Context-Aware MT
Sakarya University, Türkiye · Altınbaş University, Türkiye · Imperial College London +1
Scaling Attention Head Analysis via Gradient-Based Attribution in Context-Aware Machine Translation
Sep 23, 2026Paweł Mąka, Yusuf Can Semerci, Jan Scholtes +1Gradient-Based Attribution Attention Head Analysis
Department of Advanced Computing Sciences Maastricht University
AlexandriaX 2026: The First Shared Task on Dialectal Arabic Machine Translation
Sep 19, 2026Abdellah El Mekki, AbdelRahim A. Elmadany, Samar M. Magdy +6Context-Aware MT Machine Translation
The University of British Columbia · King Fahd University of Petroleum and Minerals · Lancaster University +4
Rosetta at AlexandriaX-2026: LoRA-Adapted NileChat for Context-Aware Dialectal Arabic Dialogue Translation
Sep 9, 2026Nada Esmaeil, Fathima Rena, Sibi Subhash +4Arabic NLP Low-Resource MT
Tanta University, Egypt · Alliance University, India · Robusta Studio, Egypt +2
Discourse Dependency: A Continuous Criterion for Translation Difficulty
Sep 4, 2026Ahrii Kim, Chanjun Park, Seong-heum KimMT Evaluation Context-Aware MT
AI-Bio Convergence Research Inst. Soongsil University · School of Software Soongsil University · Dept. of Intelligent Semiconductors Soongsil University
When to Use Extra Context: Evidence-Grounded Terminology Adaptation for Simultaneous Speech Translation
Jul 20, 2026Zeyu Yang, Satoshi NakamuraSpeech Translation Simultaneous Speech Translation
The Chinese University of Hong Kong, Shenzhen
Which Tokens Need Context? A Reference-Based Analysis of Translation Responsibility Using Fertility and Entropy
Jun 28, 2026Ramakrishna Appicharla, Baban Gain, Santanu Pal +1Context-Aware MT Machine Translation
Department of Computer Science and Engineering, Indian Institute of Technology Patna, India · 2Wipro AI Lab45, Bengaluru, India
Multilingual Reasoning Cascades Need More Context
Jun 25, 2026Arnav Mazumder, Dengjia Zhang, Shuyue Stella Li +2Cross-Lingual Reasoning in Language Models Context-Aware MT
University of Washington · Johns Hopkins University
Loong: A Human-Like Long Document Translation Agent with Observe-and-Act Adaptive Context Selection
May 28, 2026Yutong Wang, Xuebo Liu, Derek F. Wong +6Adaptive Retrieval Document-Level MT
Institute of Computing and Intelligence, Harbin Institute of Technology, Shenzhen · 2NLP2CT Lab, Department of Computer and Information Science, University of Macau · 3Huawei Translation Services Center
Language-free Experience at Expo 2025 Osaka
May 1, 2026Michael Paul, Kenji Imamura, Xiaolin Wang +2Speech Translation Simultaneous Speech Translation
National Institute of Information and Communications Technology (NICT), Japan
Cross-Preference Learning for Sentence-Level and Context-Aware Machine Translation
Mar 26, 2026Ying Li, Xinglin Lyu, Junhui Li +5Context-Aware MT Machine Translation
School of Computer Science and Technology, Soochow University, Suzhou, China · School of Computer Science and Artificial Intelligence, Zhengzhou University, Zhengzhou, China · Jiangsu Key Lab of Language Computing, China +1

Oct 17, 2026J/K move · Enter open · S save

Training with Ciphers to Enhance In-Context Terminology Learning For Translation from Rare Languages

Deevyanshu Malu, Deeptanshu Malu, Sunita Sarawagi

IIT Bombay

Machine Translation In-Context Learning Fine-Tuning Language Models Low-Resource MT Context-Aware MT

Open paper AskPDF arXiv

Fine-tuning LLMs with in-context examples (IC-Train) lets translation models adapt to new parallel data at deployment, but it is unclear whether they actually learn the translations of rare terms from those examples. We formalize this capability as in-context term learning (ICTL). We show that standard IC-Train develops this capability only weakly, and propose RareCipherFT, which strengthens it without any lexical resources. RareCipherFT pairs each training target with in-context examples that share a rare term with it. It then replaces that term with a character-shuffled cipher in both the context and the reference, so the term can only be recovered by copying from context. The ciphered fraction of training data is annealed to preserve translation quality. Across seven translation directions between English and Tamil, Assamese, Mizo, Nepali and Hausa, and four models from 1B to 7B parameters, RareCipherFT raises term recall over standard IC-Train by 5-15 absolute points without lowering COMET. Probes using synonyms, nonce words and controls for shared surface context show that these gains come from linking source terms to their in-context translations rather than from shortcuts.