BioWordVec: Improving Biomedical Word Embeddings with Subword Information and MeSH Ontology

Distributed word representations have become an essential foundation for biomedical natural language processing (BioNLP). Here we present BioWordVec: an open set of biomedical word embeddings that combines subword information from unlabelled biomedical text with a widely-used biomedical ontology called Medical Subject Headings (MeSH). Our BioWordVec data contain two embedding files “bio_embedding_intrinsic” and “bio_embedding_extrinsic”. "bio_embedding_intrinsic" is for intrinsic tasks and used to calculate or predict semantic similarity between words, terms or sentences. "bio_embedding_extrinsic" is for extrinsic tasks and used as the input for various downstream NLP tasks, such as relation extraction or text classification.Both sets are in binary format and contain 2,324,849 distinct words in total where 2,309,172 words come from the PubMed and 15,677 from MeSH. All words were converted to lowercase and the number of dimensions is 200.