BioSentVec: creating sentence embeddings for biomedical texts
Authors:
Preprint
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 MIMIC-III Clinical Database. We evaluate BioSentVec embeddings in two sentence pair similarity tasks in different 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. BioSentVec is publicly available at https://github.com/ncbi-nlp/BioSentVecKeywords
All Related Versions
This publication has 5 references indexed in Scilit:
- A comparison of word embeddings for the biomedical natural language processingJournal of Biomedical Informatics, 2018
- MedSTS: a resource for clinical semantic textual similarityLanguage Resources and Evaluation, 2018
- bigNN: An open-source big data toolkit focused on biomedical sentence classification2017
- BIOSSES: a semantic sentence similarity estimation system for the biomedical domainBioinformatics, 2017
- MIMIC-III, a freely accessible critical care databaseScientific Data, 2016