BriefGPT.xyz
Oct, 2022
通过大规模翻译丰富低资源语言的生物医学知识
Enriching Biomedical Knowledge for Low-resource Language Through Translation
HTML
PDF
Long Phan, Tai Dang, Hieu Tran, Vy Phan, Lam D. Chau...
TL;DR
本研究使用英越翻译模型将生物医学数据和基准转化为越南语，并利用大规模的越南语翻译数据训练得到了ViPubmedT5编解码Transformer模型，该模型在医学摘要和首字母缩写消歧方面取得了最先进的成果，并发布了ViMedNLI数据集用于NLP任务。
Abstract
biomedical data
and benchmarks are highly valuable yet very limited in
low-resource languages
other than English such as Vietnamese. In this paper, we make use of a state-of-the-art translation model in English-V
→