Biomedical document triage using a hierarchical attention-based capsule network
Abstract Background Biomedical document triage is the foundation of biomedical information extraction, which is important to precision medicine. Recently, some neural networks-based methods have been proposed to classify biomedical documents automatically. In the biomedical domain, documents are oft...
Main Authors: | , , , , , |
---|---|
Format: | Article |
Language: | English |
Published: |
BMC
2020-09-01
|
Series: | BMC Bioinformatics |
Subjects: | |
Online Access: | http://link.springer.com/article/10.1186/s12859-020-03673-5 |
id |
doaj-220790a2f37f45f0859bb1057c20f9ec |
---|---|
record_format |
Article |
spelling |
doaj-220790a2f37f45f0859bb1057c20f9ec2020-11-25T03:27:54ZengBMCBMC Bioinformatics1471-21052020-09-0121S1312010.1186/s12859-020-03673-5Biomedical document triage using a hierarchical attention-based capsule networkJian Wang0Mengying Li1Qishuai Diao2Hongfei Lin3Zhihao Yang4YiJia Zhang5Dalian University of TechnologyDalian University of TechnologyDalian University of TechnologyDalian University of TechnologyDalian University of TechnologyDalian University of TechnologyAbstract Background Biomedical document triage is the foundation of biomedical information extraction, which is important to precision medicine. Recently, some neural networks-based methods have been proposed to classify biomedical documents automatically. In the biomedical domain, documents are often very long and often contain very complicated sentences. However, the current methods still find it difficult to capture important features across sentences. Results In this paper, we propose a hierarchical attention-based capsule model for biomedical document triage. The proposed model effectively employs hierarchical attention mechanism and capsule networks to capture valuable features across sentences and construct a final latent feature representation for a document. We evaluated our model on three public corpora. Conclusions Experimental results showed that both hierarchical attention mechanism and capsule networks are helpful in biomedical document triage task. Our method proved itself highly competitive or superior compared with other state-of-the-art methods.http://link.springer.com/article/10.1186/s12859-020-03673-5Biomedical document triageCapsule networkHierarchical attention mechanismBiomedical literature |
collection |
DOAJ |
language |
English |
format |
Article |
sources |
DOAJ |
author |
Jian Wang Mengying Li Qishuai Diao Hongfei Lin Zhihao Yang YiJia Zhang |
spellingShingle |
Jian Wang Mengying Li Qishuai Diao Hongfei Lin Zhihao Yang YiJia Zhang Biomedical document triage using a hierarchical attention-based capsule network BMC Bioinformatics Biomedical document triage Capsule network Hierarchical attention mechanism Biomedical literature |
author_facet |
Jian Wang Mengying Li Qishuai Diao Hongfei Lin Zhihao Yang YiJia Zhang |
author_sort |
Jian Wang |
title |
Biomedical document triage using a hierarchical attention-based capsule network |
title_short |
Biomedical document triage using a hierarchical attention-based capsule network |
title_full |
Biomedical document triage using a hierarchical attention-based capsule network |
title_fullStr |
Biomedical document triage using a hierarchical attention-based capsule network |
title_full_unstemmed |
Biomedical document triage using a hierarchical attention-based capsule network |
title_sort |
biomedical document triage using a hierarchical attention-based capsule network |
publisher |
BMC |
series |
BMC Bioinformatics |
issn |
1471-2105 |
publishDate |
2020-09-01 |
description |
Abstract Background Biomedical document triage is the foundation of biomedical information extraction, which is important to precision medicine. Recently, some neural networks-based methods have been proposed to classify biomedical documents automatically. In the biomedical domain, documents are often very long and often contain very complicated sentences. However, the current methods still find it difficult to capture important features across sentences. Results In this paper, we propose a hierarchical attention-based capsule model for biomedical document triage. The proposed model effectively employs hierarchical attention mechanism and capsule networks to capture valuable features across sentences and construct a final latent feature representation for a document. We evaluated our model on three public corpora. Conclusions Experimental results showed that both hierarchical attention mechanism and capsule networks are helpful in biomedical document triage task. Our method proved itself highly competitive or superior compared with other state-of-the-art methods. |
topic |
Biomedical document triage Capsule network Hierarchical attention mechanism Biomedical literature |
url |
http://link.springer.com/article/10.1186/s12859-020-03673-5 |
work_keys_str_mv |
AT jianwang biomedicaldocumenttriageusingahierarchicalattentionbasedcapsulenetwork AT mengyingli biomedicaldocumenttriageusingahierarchicalattentionbasedcapsulenetwork AT qishuaidiao biomedicaldocumenttriageusingahierarchicalattentionbasedcapsulenetwork AT hongfeilin biomedicaldocumenttriageusingahierarchicalattentionbasedcapsulenetwork AT zhihaoyang biomedicaldocumenttriageusingahierarchicalattentionbasedcapsulenetwork AT yijiazhang biomedicaldocumenttriageusingahierarchicalattentionbasedcapsulenetwork |
_version_ |
1724586518524198912 |