xTower: A Multilingual LLM for Explaining and Correcting Translation Errors
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.
Code (0)
등록된 구현이 없습니다.
Tasks
Error UnderstandingLanguage ModelingLanguage ModellingLarge Language ModelMachine TranslationTranslationSimilar Papers 제목 키워드 기반
Automatic Correction of Human Translations
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-EditingTranslationSecoco: Self-Correcting Encoding for Neural Machine Translation
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 TranslationNMTTranslationDetecting and Correcting Syntactic Errors in Machine Translation Using Feature-Based Lexicalized Tree Adjoining Grammars
Segmenting Subtitles for Correcting ASR Segmentation Errors
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+2Quantifying the Impact of Translation Errors on Multilingual LLM Evaluation
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…