Translate Meanings, Not Just Words: IdiomKB's Role in Optimizing Idiomatic Translation with Language Models
Preprint
Abstract
To translate well, machine translation (MT) systems and general-purposed language models (LMs) need a deep understanding of both source and target languages and cultures. Therefore, idioms, with their non-compositional nature, pose particular challenges for Transformer-based systems, as literal translations often miss the intended meaning. Traditional methods, which replace idioms using existing knowledge bases (KBs), often lack scale and context awareness. Addressing these challenges, our approach prioritizes context awareness and scalability, allowing for offline storage of idioms in a manageable KB size. This ensures efficient serving with smaller models and provides a more comprehensive understanding of idiomatic expressions. We introduce a multilingual idiom KB (IdiomKB) developed using large LMs to address this. This KB facilitates better translation by smaller models, such as BLOOMZ (7.1B), Alpaca (7B), and InstructGPT (6.7B), by retrieving idioms' figurative meanings. We present a novel, GPT-4-powered metric for human-aligned evaluation, demonstrating that IdiomKB considerably boosts model performance. Human evaluations further validate our KB's quality.Keywords
All Related Versions
This publication has 12 references indexed in Scilit:
- Exploring the Use of Large Language Models for Reference-Free Text Quality Evaluation: An Empirical Study2023
- Is ChatGPT a Good NLG Evaluator? A Preliminary Study2023
- Distilling Script Knowledge from Large Language Models for Constrained Language Planning2023
- Findings of the 2022 Conference on Machine Translation (WMT22)2022
- Can Transformer be Too Compositional? Analysing Idiom Processing in Neural Machine Translation2022
- The Paradox of the Compositionality of Natural Language: A Neural Machine Translation Case Study2022
- Using IndoWordNet for Contextually Improved Machine Translation of Gujarati IdiomsInternational Journal of Advanced Computer Science and Applications, 2021
- Learning L2 idioms in a CALL environment: the role of practice intensity, modality, and idiom propertiesComputer Assisted Language Learning, 2020
- Multiword Expression Processing: A SurveyComputational Linguistics, 2017
- Does formal training in translation/interpreting affect translation strategy? Evidence from idiom translationBilingualism: Language and Cognition, 2016