A Multilingual Neural Machine Translation Model for Biomedical Data
This release aids large-scale multilingual analysis of COVID-19-related content, addressing a domain-specific need for biomedical translation.
The authors developed a multilingual neural machine translation model for biomedical text, translating from five languages into English, which performs near state-of-the-art on both generic and biomedical benchmarks and outperforms existing public models.
We release a multilingual neural machine translation model, which can be used to translate text in the biomedical domain. The model can translate from 5 languages (French, German, Italian, Korean and Spanish) into English. It is trained with large amounts of generic and biomedical data, using domain tags. Our benchmarks show that it performs near state-of-the-art both on news (generic domain) and biomedical test sets, and that it outperforms the existing publicly released models. We believe that this release will help the large-scale multilingual analysis of the digital content of the COVID-19 crisis and of its effects on society, economy, and healthcare policies. We also release a test set of biomedical text for Korean-English. It consists of 758 sentences from official guidelines and recent papers, all about COVID-19.