Cargando…

CID-GCN: An Effective Graph Convolutional Networks for Chemical-Induced Disease Relation Extraction

Automatic extraction of chemical-induced disease (CID) relation from unstructured text is of essential importance for disease treatment and drug development. In this task, some relational facts can only be inferred from the document rather than single sentence. Recently, researchers investigate grap...

Descripción completa

Detalles Bibliográficos
Autores principales: Zeng, Daojian, Zhao, Chao, Quan, Zhe
Formato: Online Artículo Texto
Lenguaje:English
Publicado: Frontiers Media S.A. 2021
Materias:
Acceso en línea:https://www.ncbi.nlm.nih.gov/pmc/articles/PMC7902761/
https://www.ncbi.nlm.nih.gov/pubmed/33643385
http://dx.doi.org/10.3389/fgene.2021.624307
_version_ 1783654594058911744
author Zeng, Daojian
Zhao, Chao
Quan, Zhe
author_facet Zeng, Daojian
Zhao, Chao
Quan, Zhe
author_sort Zeng, Daojian
collection PubMed
description Automatic extraction of chemical-induced disease (CID) relation from unstructured text is of essential importance for disease treatment and drug development. In this task, some relational facts can only be inferred from the document rather than single sentence. Recently, researchers investigate graph-based approaches to extract relations across sentences. It iteratively combines the information from neighbor nodes to model the interactions in entity mentions that exist in different sentences. Despite their success, one severe limitation of the graph-based approaches is the over-smoothing problem, which decreases the model distinguishing ability. In this paper, we propose CID-GCN, an effective Graph Convolutional Networks (GCNs) with gating mechanism, for CID relation extraction. Specifically, we construct a heterogeneous graph which contains mention, sentence and entity nodes. Then, the graph convolution operation is employed to aggregate interactive information on the constructed graph. Particularly, we combine gating mechanism with the graph convolution operation to address the over-smoothing problem. The experimental results demonstrate that our approach significantly outperforms the baselines.
format Online
Article
Text
id pubmed-7902761
institution National Center for Biotechnology Information
language English
publishDate 2021
publisher Frontiers Media S.A.
record_format MEDLINE/PubMed
spelling pubmed-79027612021-02-25 CID-GCN: An Effective Graph Convolutional Networks for Chemical-Induced Disease Relation Extraction Zeng, Daojian Zhao, Chao Quan, Zhe Front Genet Genetics Automatic extraction of chemical-induced disease (CID) relation from unstructured text is of essential importance for disease treatment and drug development. In this task, some relational facts can only be inferred from the document rather than single sentence. Recently, researchers investigate graph-based approaches to extract relations across sentences. It iteratively combines the information from neighbor nodes to model the interactions in entity mentions that exist in different sentences. Despite their success, one severe limitation of the graph-based approaches is the over-smoothing problem, which decreases the model distinguishing ability. In this paper, we propose CID-GCN, an effective Graph Convolutional Networks (GCNs) with gating mechanism, for CID relation extraction. Specifically, we construct a heterogeneous graph which contains mention, sentence and entity nodes. Then, the graph convolution operation is employed to aggregate interactive information on the constructed graph. Particularly, we combine gating mechanism with the graph convolution operation to address the over-smoothing problem. The experimental results demonstrate that our approach significantly outperforms the baselines. Frontiers Media S.A. 2021-02-10 /pmc/articles/PMC7902761/ /pubmed/33643385 http://dx.doi.org/10.3389/fgene.2021.624307 Text en Copyright © 2021 Zeng, Zhao and Quan. http://creativecommons.org/licenses/by/4.0/ This is an open-access article distributed under the terms of the Creative Commons Attribution License (CC BY). The use, distribution or reproduction in other forums is permitted, provided the original author(s) and the copyright owner(s) are credited and that the original publication in this journal is cited, in accordance with accepted academic practice. No use, distribution or reproduction is permitted which does not comply with these terms.
spellingShingle Genetics
Zeng, Daojian
Zhao, Chao
Quan, Zhe
CID-GCN: An Effective Graph Convolutional Networks for Chemical-Induced Disease Relation Extraction
title CID-GCN: An Effective Graph Convolutional Networks for Chemical-Induced Disease Relation Extraction
title_full CID-GCN: An Effective Graph Convolutional Networks for Chemical-Induced Disease Relation Extraction
title_fullStr CID-GCN: An Effective Graph Convolutional Networks for Chemical-Induced Disease Relation Extraction
title_full_unstemmed CID-GCN: An Effective Graph Convolutional Networks for Chemical-Induced Disease Relation Extraction
title_short CID-GCN: An Effective Graph Convolutional Networks for Chemical-Induced Disease Relation Extraction
title_sort cid-gcn: an effective graph convolutional networks for chemical-induced disease relation extraction
topic Genetics
url https://www.ncbi.nlm.nih.gov/pmc/articles/PMC7902761/
https://www.ncbi.nlm.nih.gov/pubmed/33643385
http://dx.doi.org/10.3389/fgene.2021.624307
work_keys_str_mv AT zengdaojian cidgcnaneffectivegraphconvolutionalnetworksforchemicalinduceddiseaserelationextraction
AT zhaochao cidgcnaneffectivegraphconvolutionalnetworksforchemicalinduceddiseaserelationextraction
AT quanzhe cidgcnaneffectivegraphconvolutionalnetworksforchemicalinduceddiseaserelationextraction