Machine Translation
New Trends for Modern Machine Translation with Large Reasoning Models
·518 words·3 mins·
loading
·
loading
AI Generated
🤗 Daily Papers
Natural Language Processing
Machine Translation
🏢 University of Edinburgh
LRMs transform MT with reasoning, handling context, culture, and nuance for better translations.
Beyond Decoder-only: Large Language Models Can be Good Encoders for Machine Translation
·6125 words·29 mins·
loading
·
loading
AI Generated
🤗 Daily Papers
Natural Language Processing
Machine Translation
🏢 NLP Lab, Northeastern University, Shenyang, China
LLMs as MT encoders enhance efficiency & generalization!
Lost in Literalism: How Supervised Training Shapes Translationese in LLMs
·3432 words·17 mins·
loading
·
loading
AI Generated
🤗 Daily Papers
Natural Language Processing
Machine Translation
🏢 Shanghai AI Laboratory
LLMs show translationese due to supervised training biases. Polishing references and filtering unnatural instances can mitigate this issue.
QE4PE: Word-level Quality Estimation for Human Post-Editing
·6157 words·29 mins·
loading
·
loading
AI Generated
🤗 Daily Papers
Natural Language Processing
Machine Translation
🏢 CLCG, University of Groningen
QE4PE: Word-level QE’s impact on MT post-editing with 42 pro-editors across English-Italian/Dutch is investigated. Usability&accuracy challenges in professional workflows are underlined.
R1-T1: Fully Incentivizing Translation Capability in LLMs via Reasoning Learning
·219 words·2 mins·
loading
·
loading
AI Generated
🤗 Daily Papers
Natural Language Processing
Machine Translation
🏢 Huawei, China
R1-T1: RL-driven framework incentivizing translation capability in LLMs via reasoning learning, achieving superior performance in multiple languages & domains.
DRT-o1: Optimized Deep Reasoning Translation via Long Chain-of-Thought
·402 words·2 mins·
loading
·
loading
AI Generated
🤗 Daily Papers
Natural Language Processing
Machine Translation
🏢 Tencent AI Lab
DRT-01 leverages long chain-of-thought reasoning to significantly boost machine translation quality, particularly for complex sentences with metaphors and similes, achieving substantial improvements o…
Shiksha: A Technical Domain focused Translation Dataset and Model for Indian Languages
·1855 words·9 mins·
loading
·
loading
AI Generated
🤗 Daily Papers
Natural Language Processing
Machine Translation
🏢 Indian Institute of Technology Madras
Shiksha: A new multilingual translation dataset and model surpasses existing benchmarks for Indian languages, focusing on scientific, technical, and educational domains.