Efficient Terminology Integration for LLM-based Translation in Specialized Domains
This addresses the challenge of accurate terminology translation in specialized domains like patent, finance, or biomedical fields, where general methods often fail, though it is incremental as it builds on existing LLM techniques.
The paper tackles the problem of specialized terminology integration in LLM-based translation by introducing a methodology using term extraction, glossary creation with Trie Tree, and data reconstruction, achieving the highest translation score in the WMT patent task.
Traditional machine translation methods typically involve training models directly on large parallel corpora, with limited emphasis on specialized terminology. However, In specialized fields such as patent, finance, or biomedical domains, terminology is crucial for translation, with many terms that needs to be translated following agreed-upon conventions. In this paper we introduce a methodology that efficiently trains models with a smaller amount of data while preserving the accuracy of terminology translation. We achieve this through a systematic process of term extraction and glossary creation using the Trie Tree algorithm, followed by data reconstruction to teach the LLM how to integrate these specialized terms. This methodology enhances the model's ability to handle specialized terminology and ensures high-quality translations, particularly in fields where term consistency is crucial. Our approach has demonstrated exceptional performance, achieving the highest translation score among participants in the WMT patent task to date, showcasing its effectiveness and broad applicability in specialized translation domains where general methods often fall short.