BioNMT: A Biomedical Neural Machine Translation System

IAENG Internaitonal journal of computer science

article

Hongtao Liu¹  Yanchun Liang¹  Liupu Wang²  Xiaoyue Feng²  Renchu Guan¹ 

[1] Zhuhai Sub Laboratory of Key Laboratory of Symbol Computation and Knowledge Engineering of Ministry of Education, Zhuhai College of Jilin University Zhuhai;Key Laboratory of Symbol Computation and Knowledge Engineering of Ministry of Education, College of Computer Science and Technology, Jilin University

关键词: neural machine translation;    Transformer;    self-attention;    semantic disambiguation;   

DOI  :  10.15837/ijccc.2020.6.3988

学科分类：计算机科学（综合）

来源: International Association of Engineers

【 摘 要 】

To solve the problem of translation of professional vocabulary in the biomedical field and help biological researchers to translate and understand foreign language documents, we proposed a semantic disambiguation model and external dictionaries to build a novel translation model for biomedical texts based on the transformer model. The proposed biomedical neural machine translation system (BioNMT) adopts the sequence-to-sequence translation framework, which is based on deep neural networks. To construct the specialized vocabulary of biology and medicine, a hybrid corpus was obtained using a crawler system extracting from universal corpus and biomedical corpus. The experimental results showed that BioNMT which composed by professional biological dictionary and Transformer model increased the bilingual evaluation understudy (BLEU) value by 14.14%, and the perplexity was reduced by 40%. And compared with Google Translation System and Baidu Translation System, BioNMT achieved better translations about paragraphs and resolve the ambiguity of biomedical name entities to greatly improved.

【 授权许可】

CC BY