On Creating an English-Thai Code-switched Machine Translation in Medical Domain
Issued Date
2024-01-01
Resource Type
Scopus ID
2-s2.0-85217615242
Journal Title
EMNLP 2024 - 2024 Conference on Empirical Methods in Natural Language Processing, Findings of EMNLP 2024
Start Page
6055
End Page
6073
Rights Holder(s)
SCOPUS
Bibliographic Citation
EMNLP 2024 - 2024 Conference on Empirical Methods in Natural Language Processing, Findings of EMNLP 2024 (2024) , 6055-6073
Suggested Citation
Pengpun P., Tiankanon K., Chinkamol A., Kinchagawat J., Chairuengjitjaras P., Supholkhan P., Aussavavirojekul P., Boonnag C., Veerakanjana K., Phimsiri H., Sae-Jia B., Sataudom N., Ittichaiwong P., Limkonchotiwat P. On Creating an English-Thai Code-switched Machine Translation in Medical Domain. EMNLP 2024 - 2024 Conference on Empirical Methods in Natural Language Processing, Findings of EMNLP 2024 (2024) , 6055-6073. 6073. Retrieved from: https://repository.li.mahidol.ac.th/handle/20.500.14594/105340
Title
On Creating an English-Thai Code-switched Machine Translation in Medical Domain
Corresponding Author(s)
Other Contributor(s)
Abstract
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.