paper-with-me

Papers

xTower: A Multilingual LLM for Explaining and Correcting Translation Errors

2024-06-27 · Marcos Treviso, Nuno M. Guerreiro, Sweta Agrawal, Ricardo Rei, José Pombal, Tania Vaz, Helena Wu, Beatriz Silva, Daan van Stigt, André F. T. Martins

While machine translation (MT) systems are achieving increasingly strong performance on benchmarks, they often produce translations with errors and anomalies. Understanding these errors can potentially help improve the translation quality and user experience. This paper introduces xTower, an open large language model (LLM) built on top of TowerBase designed to provide free-text explanations for translation errors in order to guide the generation of a corrected translation. The quality of the generated explanations by xTower are assessed via both intrinsic and extrinsic evaluation. We ask expert translators to evaluate the quality of the explanations across two dimensions: relatedness towards the error span being explained and helpfulness in error understanding and improving translation quality. Extrinsically, we test xTower across various experimental setups in generating translation corrections, demonstrating significant improvements in translation quality. Our findings highlight xTower's potential towards not only producing plausible and helpful explanations of automatic translations, but also leveraging them to suggest corrected translations.

📄 PDF Abstract BibTeX arXiv:2406.19482

Code (0)

등록된 구현이 없습니다.

Tasks

Error UnderstandingLanguage ModelingLanguage ModellingLarge Language ModelMachine TranslationTranslation

Similar Papers 제목 키워드 기반

Automatic Correction of Human Translations

2022-06-17 · NAACL 2022 7 · Jessy Lin, Geza Kovacs, Aditya Shastry, Joern Wuebker 외

We introduce translation error correction (TEC), the task of automatically correcting human-generated translations. Imperfections in machine translations (MT) have long motivated systems for improving translations post-h…

Automatic Post-EditingTranslation

Secoco: Self-Correcting Encoding for Neural Machine Translation

2021-08-27 · Findings (EMNLP) 2021 11 · Tao Wang, Chengqi Zhao, Mingxuan Wang, Lei LI 외

This paper presents Self-correcting Encoding (Secoco), a framework that effectively deals with input noise for robust neural machine translation by introducing self-correcting predictors. Different from previous robust a…

Machine TranslationNMTTranslation

Detecting and Correcting Syntactic Errors in Machine Translation Using Feature-Based Lexicalized Tree Adjoining Grammars

2012-09-01 · ROCLINGIJCLCLP 2012 9 · Wei-Yun Ma, Kathleen McKeown
Machine TranslationTranslation

Segmenting Subtitles for Correcting ASR Segmentation Errors

2021-04-16 · EACL 2021 2 · David Wan, Chris Kedzie, Faisal Ladhak, Elsbeth Turcan 외

Typical ASR systems segment the input audio into utterances using purely acoustic information, which may not resemble the sentence-like units that are expected by conventional machine translation (MT) systems for Spoken …

Information RetrievalMachine TranslationRetrievalSegmentation+2

Quantifying the Impact of Translation Errors on Multilingual LLM Evaluation

2026-05-24 · Klaudia-Doris Thellmann, Bernhard Stadler, Michael Färber, Jens Lehmann arxiv

Machine-translated benchmarks are widely used to assess the multilingual capabilities of large language models (LLMs), yet translation errors in these benchmarks remain underexplored, raising concerns about the reliabili…