Cargando…

Document-Level Biomedical Relation Extraction Using Graph Convolutional Network and Multihead Attention: Algorithm Development and Validation

BACKGROUND: Automatically extracting relations between chemicals and diseases plays an important role in biomedical text mining. Chemical-disease relation (CDR) extraction aims at extracting complex semantic relationships between entities in documents, which contain intrasentence and intersentence r...

Descripción completa

Detalles Bibliográficos
Autores principales: Wang, Jian, Chen, Xiaoyu, Zhang, Yu, Zhang, Yijia, Wen, Jiabin, Lin, Hongfei, Yang, Zhihao, Wang, Xin
Formato: Online Artículo Texto
Lenguaje:English
Publicado: JMIR Publications 2020
Materias:
Acceso en línea:https://www.ncbi.nlm.nih.gov/pmc/articles/PMC7458061/
https://www.ncbi.nlm.nih.gov/pubmed/32459636
http://dx.doi.org/10.2196/17638
_version_ 1783576120217567232
author Wang, Jian
Chen, Xiaoyu
Zhang, Yu
Zhang, Yijia
Wen, Jiabin
Lin, Hongfei
Yang, Zhihao
Wang, Xin
author_facet Wang, Jian
Chen, Xiaoyu
Zhang, Yu
Zhang, Yijia
Wen, Jiabin
Lin, Hongfei
Yang, Zhihao
Wang, Xin
author_sort Wang, Jian
collection PubMed
description BACKGROUND: Automatically extracting relations between chemicals and diseases plays an important role in biomedical text mining. Chemical-disease relation (CDR) extraction aims at extracting complex semantic relationships between entities in documents, which contain intrasentence and intersentence relations. Most previous methods did not consider dependency syntactic information across the sentences, which are very valuable for the relations extraction task, in particular, for extracting the intersentence relations accurately. OBJECTIVE: In this paper, we propose a novel end-to-end neural network based on the graph convolutional network (GCN) and multihead attention, which makes use of the dependency syntactic information across the sentences to improve CDR extraction task. METHODS: To improve the performance of intersentence relation extraction, we constructed a document-level dependency graph to capture the dependency syntactic information across sentences. GCN is applied to capture the feature representation of the document-level dependency graph. The multihead attention mechanism is employed to learn the relatively important context features from different semantic subspaces. To enhance the input representation, the deep context representation is used in our model instead of traditional word embedding. RESULTS: We evaluate our method on CDR corpus. The experimental results show that our method achieves an F-measure of 63.5%, which is superior to other state-of-the-art methods. In the intrasentence level, our method achieves a precision, recall, and F-measure of 59.1%, 81.5%, and 68.5%, respectively. In the intersentence level, our method achieves a precision, recall, and F-measure of 47.8%, 52.2%, and 49.9%, respectively. CONCLUSIONS: The GCN model can effectively exploit the across sentence dependency information to improve the performance of intersentence CDR extraction. Both the deep context representation and multihead attention are helpful in the CDR extraction task.
format Online
Article
Text
id pubmed-7458061
institution National Center for Biotechnology Information
language English
publishDate 2020
publisher JMIR Publications
record_format MEDLINE/PubMed
spelling pubmed-74580612020-09-03 Document-Level Biomedical Relation Extraction Using Graph Convolutional Network and Multihead Attention: Algorithm Development and Validation Wang, Jian Chen, Xiaoyu Zhang, Yu Zhang, Yijia Wen, Jiabin Lin, Hongfei Yang, Zhihao Wang, Xin JMIR Med Inform Original Paper BACKGROUND: Automatically extracting relations between chemicals and diseases plays an important role in biomedical text mining. Chemical-disease relation (CDR) extraction aims at extracting complex semantic relationships between entities in documents, which contain intrasentence and intersentence relations. Most previous methods did not consider dependency syntactic information across the sentences, which are very valuable for the relations extraction task, in particular, for extracting the intersentence relations accurately. OBJECTIVE: In this paper, we propose a novel end-to-end neural network based on the graph convolutional network (GCN) and multihead attention, which makes use of the dependency syntactic information across the sentences to improve CDR extraction task. METHODS: To improve the performance of intersentence relation extraction, we constructed a document-level dependency graph to capture the dependency syntactic information across sentences. GCN is applied to capture the feature representation of the document-level dependency graph. The multihead attention mechanism is employed to learn the relatively important context features from different semantic subspaces. To enhance the input representation, the deep context representation is used in our model instead of traditional word embedding. RESULTS: We evaluate our method on CDR corpus. The experimental results show that our method achieves an F-measure of 63.5%, which is superior to other state-of-the-art methods. In the intrasentence level, our method achieves a precision, recall, and F-measure of 59.1%, 81.5%, and 68.5%, respectively. In the intersentence level, our method achieves a precision, recall, and F-measure of 47.8%, 52.2%, and 49.9%, respectively. CONCLUSIONS: The GCN model can effectively exploit the across sentence dependency information to improve the performance of intersentence CDR extraction. Both the deep context representation and multihead attention are helpful in the CDR extraction task. JMIR Publications 2020-07-31 /pmc/articles/PMC7458061/ /pubmed/32459636 http://dx.doi.org/10.2196/17638 Text en ©Jian Wang, Xiaoyu Chen, Yu Zhang, Yijia Zhang, Jiabin Wen, Hongfei Lin, Zhihao Yang, Xin Wang. Originally published in JMIR Medical Informatics (http://medinform.jmir.org), 31.07.2020. https://creativecommons.org/licenses/by/4.0/ This is an open-access article distributed under the terms of the Creative Commons Attribution License (https://creativecommons.org/licenses/by/4.0/), which permits unrestricted use, distribution, and reproduction in any medium, provided the original work, first published in JMIR Medical Informatics, is properly cited. The complete bibliographic information, a link to the original publication on http://medinform.jmir.org/, as well as this copyright and license information must be included.
spellingShingle Original Paper
Wang, Jian
Chen, Xiaoyu
Zhang, Yu
Zhang, Yijia
Wen, Jiabin
Lin, Hongfei
Yang, Zhihao
Wang, Xin
Document-Level Biomedical Relation Extraction Using Graph Convolutional Network and Multihead Attention: Algorithm Development and Validation
title Document-Level Biomedical Relation Extraction Using Graph Convolutional Network and Multihead Attention: Algorithm Development and Validation
title_full Document-Level Biomedical Relation Extraction Using Graph Convolutional Network and Multihead Attention: Algorithm Development and Validation
title_fullStr Document-Level Biomedical Relation Extraction Using Graph Convolutional Network and Multihead Attention: Algorithm Development and Validation
title_full_unstemmed Document-Level Biomedical Relation Extraction Using Graph Convolutional Network and Multihead Attention: Algorithm Development and Validation
title_short Document-Level Biomedical Relation Extraction Using Graph Convolutional Network and Multihead Attention: Algorithm Development and Validation
title_sort document-level biomedical relation extraction using graph convolutional network and multihead attention: algorithm development and validation
topic Original Paper
url https://www.ncbi.nlm.nih.gov/pmc/articles/PMC7458061/
https://www.ncbi.nlm.nih.gov/pubmed/32459636
http://dx.doi.org/10.2196/17638
work_keys_str_mv AT wangjian documentlevelbiomedicalrelationextractionusinggraphconvolutionalnetworkandmultiheadattentionalgorithmdevelopmentandvalidation
AT chenxiaoyu documentlevelbiomedicalrelationextractionusinggraphconvolutionalnetworkandmultiheadattentionalgorithmdevelopmentandvalidation
AT zhangyu documentlevelbiomedicalrelationextractionusinggraphconvolutionalnetworkandmultiheadattentionalgorithmdevelopmentandvalidation
AT zhangyijia documentlevelbiomedicalrelationextractionusinggraphconvolutionalnetworkandmultiheadattentionalgorithmdevelopmentandvalidation
AT wenjiabin documentlevelbiomedicalrelationextractionusinggraphconvolutionalnetworkandmultiheadattentionalgorithmdevelopmentandvalidation
AT linhongfei documentlevelbiomedicalrelationextractionusinggraphconvolutionalnetworkandmultiheadattentionalgorithmdevelopmentandvalidation
AT yangzhihao documentlevelbiomedicalrelationextractionusinggraphconvolutionalnetworkandmultiheadattentionalgorithmdevelopmentandvalidation
AT wangxin documentlevelbiomedicalrelationextractionusinggraphconvolutionalnetworkandmultiheadattentionalgorithmdevelopmentandvalidation