BioSentVec: creating sentence embeddings for biomedical texts

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 intr...

Full description

Saved in:
Bibliographic Details
Main Authors: Chen, Qingyu, Peng, Yifan, Lu, Zhiyong
Format: Conference Proceeding
Language:English
Subjects:
Biomedical Text Mining
Sentence Embeddings
Citations: Items that cite this one
Online Access:Request full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary: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.
ISSN:2575-2634
DOI:10.1109/ICHI.2019.8904728