Back

Enriching Biomedical Knowledge for Low-resource Language Through Translation

Phan, L.; Dang, T.; Tran, H.; Phan, V.; Chau, L. D.; Trinh, T. H.

2022-10-14 bioinformatics
10.1101/2022.10.11.511776 bioRxiv
Show 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-theart translation model in English-Vietnamese to translate and produce both pretrained as well as supervised data in the biomedical domains. Thanks to such large-scale translation, we introduce ViPubmedT5, a pretrained Encoder-Decoder Transformer model trained on 20 million translated abstracts from the high-quality public PubMed corpus. ViPubMedT5 demonstrates state-of-the-art results on two different biomedical benchmarks in summarization and acronym disambiguation. Further, we release ViMedNLI a new NLP task in Vietnamese translated from MedNLI using the recently public En-vi translation model and carefully refined by human experts, with evaluations of existing methods against ViPubmedT5.

Matching journals

The top 4 journals account for 50% of the predicted probability mass.

50% of probability mass above

"Similar papers" are the closest papers from that journal in the model's embedding space. They show what the match is built on, but the ranking comes mostly from a classifier over the whole training set, not from these examples alone.