Back to Search
Start Over
Using Character-Level and Entity-Level Representations to Enhance Bidirectional Encoder Representation From Transformers-Based Clinical Semantic Textual Similarity Model: ClinicalSTS Modeling Study
- Source :
- JMIR Medical Informatics, JMIR Medical Informatics, Vol 8, Iss 12, p e23357 (2020)
- Publication Year :
- 2020
- Publisher :
- JMIR Publications, 2020.
-
Abstract
- Background With the popularity of electronic health records (EHRs), the quality of health care has been improved. However, there are also some problems caused by EHRs, such as the growing use of copy-and-paste and templates, resulting in EHRs of low quality in content. In order to minimize data redundancy in different documents, Harvard Medical School and Mayo Clinic organized a national natural language processing (NLP) clinical challenge (n2c2) on clinical semantic textual similarity (ClinicalSTS) in 2019. The task of this challenge is to compute the semantic similarity among clinical text snippets. Objective In this study, we aim to investigate novel methods to model ClinicalSTS and analyze the results. Methods We propose a semantically enhanced text matching model for the 2019 n2c2/Open Health NLP (OHNLP) challenge on ClinicalSTS. The model includes 3 representation modules to encode clinical text snippet pairs at different levels: (1) character-level representation module based on convolutional neural network (CNN) to tackle the out-of-vocabulary problem in NLP; (2) sentence-level representation module that adopts a pretrained language model bidirectional encoder representation from transformers (BERT) to encode clinical text snippet pairs; and (3) entity-level representation module to model clinical entity information in clinical text snippets. In the case of entity-level representation, we compare 2 methods. One encodes entities by the entity-type label sequence corresponding to text snippet (called entity I), whereas the other encodes entities by their representation in MeSH, a knowledge graph in the medical domain (called entity II). Results We conduct experiments on the ClinicalSTS corpus of the 2019 n2c2/OHNLP challenge for model performance evaluation. The model only using BERT for text snippet pair encoding achieved a Pearson correlation coefficient (PCC) of 0.848. When character-level representation and entity-level representation are individually added into our model, the PCC increased to 0.857 and 0.854 (entity I)/0.859 (entity II), respectively. When both character-level representation and entity-level representation are added into our model, the PCC further increased to 0.861 (entity I) and 0.868 (entity II). Conclusions Experimental results show that both character-level information and entity-level information can effectively enhance the BERT-based STS model.
- Subjects :
- Computer science
Computer applications to medicine. Medical informatics
R858-859.7
Health Informatics
02 engineering and technology
computer.software_genre
Convolutional neural network
03 medical and health sciences
Health Information Management
Semantic similarity
Similarity (psychology)
0202 electrical engineering, electronic engineering, information engineering
clinical semantic textual similarity
natural language processing
030304 developmental biology
0303 health sciences
Original Paper
business.industry
Deep learning
Representation (systemics)
deep learning
Snippet
Similitude
knowledge graph
020201 artificial intelligence & image processing
Artificial intelligence
Language model
business
computer
Natural language processing
Subjects
Details
- Language :
- English
- ISSN :
- 22919694
- Volume :
- 8
- Issue :
- 12
- Database :
- OpenAIRE
- Journal :
- JMIR Medical Informatics
- Accession number :
- edsair.doi.dedup.....7998552d0af7f17447a21793e8cc95d1