On Creating an English-Thai Code-switched Machine Translation in Medical Domain
This work addresses the challenge of accurate medical terminology translation for healthcare and knowledge dissemination, though it is incremental as it builds on existing translation technologies with a domain-specific adaptation.
The paper tackled the problem of English-Thai machine translation in the medical domain by developing a code-switched translation method that maintains English medical terms, resulting in competitive performance against baselines like Google NMT and GPT models, with human evaluations showing medical professionals significantly prefer these translations even at a slight cost to fluency.
Machine translation (MT) in the medical domain plays a pivotal role in enhancing healthcare quality and disseminating medical knowledge. Despite advancements in English-Thai MT technology, common MT approaches often underperform in the medical field due to their inability to precisely translate medical terminologies. Our research prioritizes not merely improving translation accuracy but also maintaining medical terminology in English within the translated text through code-switched (CS) translation. We developed a method to produce CS medical translation data, fine-tuned a CS translation model with this data, and evaluated its performance against strong baselines, such as Google Neural Machine Translation (NMT) and GPT-3.5/GPT-4. Our model demonstrated competitive performance in automatic metrics and was highly favored in human preference evaluations. Our evaluation result also shows that medical professionals significantly prefer CS translations that maintain critical English terms accurately, even if it slightly compromises fluency. Our code and test set are publicly available https://github.com/preceptorai-org/NLLB_CS_EM_NLP2024.