BioSentVec: creating sentence embeddings for biomedical texts
TL
TL;DR
This work introduces BioSentVec: the first open set of sentence embeddings trained with over 30 million documents from both scholarly articles in PubMed and clinical notes in the MIMICIII Clinical Database and expects it to facilitate the research and development in biomedical text mining and to complement the existing resources in biomedical word embeddins.
Abstract
Sentence embeddings have become an essential part of today’s natural language processing (NLP) systems, especially together advanced deep learning methods. Although pre-trained sentence encoders are available in the general domain, none exists for biomedical texts to date. In this work, we introduce BioSentVec: the first open set of sentence embeddings trained with over 30 million documents from both scholarly articles in PubMed and clinical notes in the MIMICIII Clinical Database. We evaluate BioSentVec embeddings in two sentence pair similarity tasks in different biomedical text genres. Our benchmarking results demonstrate that the BioSentVec embeddings can better capture sentence semantics compared to the other competitive alternatives and achieve state-of-the-art performance in both tasks. We expect BioSentVec to facilitate the research and development in biomedical text mining and to complement the existing resources in biomedical word embeddings. The embeddings are publicly available at https://github.com/ncbi-nlp/BioSentVec.
References23 items
1
LitSense: making sense of biomedical literature at sentence level
2
Unsupervised low-dimensional vector representations for words, phrases and text that are transparent, scalable, and produce similarity metrics that are not redundant with neural embeddings
3
MedSTS: a resource for clinical semantic textual similarity
4
Sentence Similarity Measures Revisited: Ranking Sentences in PubMed Documents
5