Translate Meanings, Not Just Words: IdiomKB’s Role in Optimizing Idiomatic Translation with Language Models
Open Access
- 24 March 2024
- journal article
- research article
- Published by Association for the Advancement of Artificial Intelligence (AAAI) in Proceedings of the AAAI Conference on Artificial Intelligence
- Vol. 38 (17) , 18554-18563
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 10 references indexed in Scilit:
- Multilingual Machine Translation with Large Language Models: Empirical Results and Analysis2024
- 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
- 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
- Construction of an idiom corpus and its application to idiom identification based on WSD incorporating idiom-specific features2008