On Creating an English-Thai Code-switched Machine Translation in Medical Domain

Parinthapat Pengpun, Krittamate Tiankanon, Amrest Chinkamol, Jiramet Kinchagawat, Pitchaya Chairuengjitjaras +9 more
10/21/2024
cs.CLcs.AIcs.LG

Official code: preceptorai-org/NLLB_CS_EM_NLP2024 (2 stars, MIT, last commit 2024-10-22).

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.

View on arXivView PDF

Code Implementations(1)

preceptorai-org/NLLB_CS_EM_NLP2024Official100%
MIT

[EMNLP 2024 Finding] Implementation for the paper "On Creating an English-Thai Code-switched Machine Translation in Medical Domain"

20Python, Jupyter NotebookSep 30, 20241 years agoMIT

Similar Papers

Instruction-tuned Large Language Models for Machine Translation in the Medical Domain

83% match2024

Creating Domain-Specific Translation Memories for Machine Translation Fine-tuning: The TRENCARD Bilingual Cardiology Corpus

82% match2024

Improving Vietnamese-English Medical Machine Translation

82% match2024

Comparing Large Language Models and Traditional Machine Translation Tools for Translating Medical Consultation Summaries: A Pilot Study

82% match2025

LLMs-in-the-loop Part-1: Expert Small AI Models for Bio-Medical Text Translation

82% match2024

TULUN: Transparent and Adaptable Low-resource Machine Translation

82% match1 repo52025

Cite this paper

@article{pengpun2024creating,
  title  = {On Creating an English-Thai Code-switched Machine Translation in Medical Domain},
  author = {Parinthapat Pengpun and Krittamate Tiankanon and Amrest Chinkamol and Jiramet Kinchagawat and Pitchaya Chairuengjitjaras and Pasit Supholkhan and Pubordee Aussavavirojekul and Chiraphat Boonnag and Kanyakorn Veerakanjana and Hirunkul Phimsiri and Boonthicha Sae-jia and Nattawach Sataudom and Piyalitt Ittichaiwong and Peerat Limkonchotiwat},
  year   = {2024},
  eprint = {2410.16221},
  archivePrefix = {arXiv},
  url    = {http://arxiv.org/abs/2410.16221v1}
}

Add a badge to your README

Shows whether official code is linked for this paper.

Code of Paper badge
[![Code of Paper](https://codeofpaper.com/badge/2410.16221.svg)](https://codeofpaper.com/paper/2410.16221)

Discussion