Summary of On Creating An English-thai Code-switched Machine Translation in Medical Domain, by Parinthapat Pengpun et al.

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

by Parinthapat Pengpun, Krittamate Tiankanon, Amrest Chinkamol, Jiramet Kinchagawat, Pitchaya Chairuengjitjaras, Pasit Supholkhan, Pubordee Aussavavirojekul, Chiraphat Boonnag, Kanyakorn Veerakanjana, Hirunkul Phimsiri, Boonthicha Sae-jia, Nattawach Sataudom, Piyalitt Ittichaiwong, Peerat Limkonchotiwat

First submitted to arxiv on: 21 Oct 2024

GrooveSquid.com Paper Summaries

GrooveSquid.com’s goal is to make artificial intelligence research accessible by summarizing AI papers in simpler terms. Each summary below covers the same AI paper, written at different levels of difficulty. The medium difficulty and low difficulty versions are original summaries written by GrooveSquid.com, while the high difficulty version is the paper’s original abstract. Feel free to learn from the version that suits you best!

Summary difficulty	Written by	Summary
High	Paper authors	High Difficulty Summary Read the original abstract here
Medium	GrooveSquid.com (original content)	Medium Difficulty Summary Machine translation in the medical domain is crucial for enhancing healthcare quality and disseminating medical knowledge. Despite advancements in English-Thai machine translation technology, common approaches often underperform due to their inability to accurately translate medical terminologies. Our research prioritizes not only 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 like 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. Medical professionals prefer CS translations that maintain critical English terms accurately, even if it slightly compromises fluency.
Low	GrooveSquid.com (original content)	Low Difficulty Summary Machine translation is important for healthcare and sharing medical information. Even though technology has improved, some approaches don’t translate medical words well. Our research focuses on making sure medical terminology stays the same in translated text. We created a method to make this happen, tested our model against strong competitors, and showed it works well. People prefer translations that keep important English terms accurate, even if they’re not perfect.