Translate Meanings, Not Just Words: IdiomKB's Role in Optimizing Idiomatic Translation with Language Models
This addresses the problem of inaccurate idiomatic translation for users of MT systems and LMs, offering a scalable and context-aware solution, though it is incremental as it builds on existing knowledge base methods.
The paper tackled the challenge of translating idioms with non-compositional meanings in machine translation and language models by introducing IdiomKB, a multilingual idiom knowledge base, which improved translation performance in smaller models like BLOOMZ and Alpaca, as validated by a GPT-4-powered metric and human evaluations.
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.