Entity recognition in Chinese clinical text using attention-based CNN-LSTM-CRF. View Full Text


Ontology type: schema:ScholarlyArticle      Open Access: True


Article Info

DATE

2019-04

AUTHORS

Buzhou Tang, Xiaolong Wang, Jun Yan, Qingcai Chen

ABSTRACT

BACKGROUND: Clinical entity recognition as a fundamental task of clinical text processing has been attracted a great deal of attention during the last decade. However, most studies focus on clinical text in English rather than other languages. Recently, a few researchers have began to study entity recognition in Chinese clinical text. METHODS: In this paper, a novel deep neural network, called attention-based CNN-LSTM-CRF, is proposed to recognize entities in Chinese clinical text. Attention-based CNN-LSTM-CRF is an extension of LSTM-CRF by introducing a CNN (convolutional neural network) layer after the input layer to capture local context information of words of interest and an attention layer before the CRF layer to select relevant words in the same sentence. RESULTS: In order to evaluate the proposed method, we compare it with other two currently popular methods, CRF (conditional random field) and LSTM-CRF, on two benchmark datasets. One of the datasets is publically available and only contains contiguous clinical entities, and the other one is constructed by us and contains contiguous and discontiguous clinical entities. Experimental results show that attention-based CNN-LSTM-CRF outperforms CRF and LSTM-CRF. CONCLUSIONS: CNN and attention mechanism are individually beneficial to LSTM-CRF-based Chinese clinical entity recognition system, no matter whether contiguous clinical entities are considered. The conribution of attention mechanism is greater than CNN. More... »

PAGES

74

References to SciGraph publications

Identifiers

URI

http://scigraph.springernature.com/pub.10.1186/s12911-019-0787-y

DOI

http://dx.doi.org/10.1186/s12911-019-0787-y

DIMENSIONS

https://app.dimensions.ai/details/publication/pub.1113181816

PUBMED

https://www.ncbi.nlm.nih.gov/pubmed/30943972


Indexing Status Check whether this publication has been indexed by Scopus and Web Of Science using the SN Indexing Status Tool
Incoming Citations Browse incoming citations for this publication using opencitations.net

JSON-LD is the canonical representation for SciGraph data.

TIP: You can open this SciGraph record using an external JSON-LD service: JSON-LD Playground Google SDTT

[
  {
    "@context": "https://springernature.github.io/scigraph/jsonld/sgcontext.json", 
    "about": [
      {
        "id": "http://purl.org/au-research/vocabulary/anzsrc-for/2008/0801", 
        "inDefinedTermSet": "http://purl.org/au-research/vocabulary/anzsrc-for/2008/", 
        "name": "Artificial Intelligence and Image Processing", 
        "type": "DefinedTerm"
      }, 
      {
        "id": "http://purl.org/au-research/vocabulary/anzsrc-for/2008/08", 
        "inDefinedTermSet": "http://purl.org/au-research/vocabulary/anzsrc-for/2008/", 
        "name": "Information and Computing Sciences", 
        "type": "DefinedTerm"
      }
    ], 
    "author": [
      {
        "affiliation": {
          "alternateName": "Harbin Institute of Technology", 
          "id": "https://www.grid.ac/institutes/grid.19373.3f", 
          "name": [
            "Key Laboratory of Network Oriented Intelligent Computation, Harbin Institute of Technology, (Shenzhen), Shenzhen, 518055, China."
          ], 
          "type": "Organization"
        }, 
        "familyName": "Tang", 
        "givenName": "Buzhou", 
        "type": "Person"
      }, 
      {
        "affiliation": {
          "alternateName": "Harbin Institute of Technology", 
          "id": "https://www.grid.ac/institutes/grid.19373.3f", 
          "name": [
            "Key Laboratory of Network Oriented Intelligent Computation, Harbin Institute of Technology, (Shenzhen), Shenzhen, 518055, China."
          ], 
          "type": "Organization"
        }, 
        "familyName": "Wang", 
        "givenName": "Xiaolong", 
        "type": "Person"
      }, 
      {
        "affiliation": {
          "name": [
            "Yidu Cloud (Beijing) Technology Co., Ltd, Beijing, 100191, China."
          ], 
          "type": "Organization"
        }, 
        "familyName": "Yan", 
        "givenName": "Jun", 
        "type": "Person"
      }, 
      {
        "affiliation": {
          "alternateName": "Harbin Institute of Technology", 
          "id": "https://www.grid.ac/institutes/grid.19373.3f", 
          "name": [
            "Key Laboratory of Network Oriented Intelligent Computation, Harbin Institute of Technology, (Shenzhen), Shenzhen, 518055, China. qingcai.chen@gmail.com."
          ], 
          "type": "Organization"
        }, 
        "familyName": "Chen", 
        "givenName": "Qingcai", 
        "type": "Person"
      }
    ], 
    "citation": [
      {
        "id": "https://doi.org/10.1136/amiajnl-2013-002381", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1005894580"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "https://doi.org/10.1016/j.jbi.2015.06.007", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1036391306"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "https://doi.org/10.1136/jamia.2010.003947", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1040096592"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "https://doi.org/10.1136/amiajnl-2013-001628", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1041818540"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "sg:pub.10.1007/978-3-642-40802-1_24", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1043419029", 
          "https://doi.org/10.1007/978-3-642-40802-1_24"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "sg:pub.10.1186/s12859-017-1476-4", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1083399581", 
          "https://doi.org/10.1186/s12859-017-1476-4"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "sg:pub.10.1186/s12859-017-1476-4", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1083399581", 
          "https://doi.org/10.1186/s12859-017-1476-4"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "sg:pub.10.1186/s12911-017-0468-7", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1090363539", 
          "https://doi.org/10.1186/s12911-017-0468-7"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "sg:pub.10.1186/s12911-017-0468-7", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1090363539", 
          "https://doi.org/10.1186/s12911-017-0468-7"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "https://doi.org/10.1093/bioinformatics/btx761", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1092960287"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "https://doi.org/10.1093/bioinformatics/btx761", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1092960287"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "https://doi.org/10.18653/v1/s15-2136", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1099096359"
        ], 
        "type": "CreativeWork"
      }
    ], 
    "datePublished": "2019-04", 
    "datePublishedReg": "2019-04-01", 
    "description": "BACKGROUND: Clinical entity recognition as a fundamental task of clinical text processing has been attracted a great deal of attention during the last decade. However, most studies focus on clinical text in English rather than other languages. Recently, a few researchers have began to study entity recognition in Chinese clinical text.\nMETHODS: In this paper, a novel deep neural network, called attention-based CNN-LSTM-CRF, is proposed to recognize entities in Chinese clinical text. Attention-based CNN-LSTM-CRF is an extension of LSTM-CRF by introducing a CNN (convolutional neural network) layer after the input layer to capture local context information of words of interest and an attention layer before the CRF layer to select relevant words in the same sentence.\nRESULTS: In order to evaluate the proposed method, we compare it with other two currently popular methods, CRF (conditional random field) and LSTM-CRF, on two benchmark datasets. One of the datasets is publically available and only contains contiguous clinical entities, and the other one is constructed by us and contains contiguous and discontiguous clinical entities. Experimental results show that attention-based CNN-LSTM-CRF outperforms CRF and LSTM-CRF.\nCONCLUSIONS: CNN and attention mechanism are individually beneficial to LSTM-CRF-based Chinese clinical entity recognition system, no matter whether contiguous clinical entities are considered. The conribution of attention mechanism is greater than CNN.", 
    "genre": "research_article", 
    "id": "sg:pub.10.1186/s12911-019-0787-y", 
    "inLanguage": [
      "en"
    ], 
    "isAccessibleForFree": true, 
    "isPartOf": [
      {
        "id": "sg:journal.1028432", 
        "issn": [
          "1472-6947"
        ], 
        "name": "BMC Medical Informatics and Decision Making", 
        "type": "Periodical"
      }, 
      {
        "issueNumber": "Suppl 3", 
        "type": "PublicationIssue"
      }, 
      {
        "type": "PublicationVolume", 
        "volumeNumber": "19"
      }
    ], 
    "name": "Entity recognition in Chinese clinical text using attention-based CNN-LSTM-CRF.", 
    "pagination": "74", 
    "productId": [
      {
        "name": "doi", 
        "type": "PropertyValue", 
        "value": [
          "10.1186/s12911-019-0787-y"
        ]
      }, 
      {
        "name": "dimensions_id", 
        "type": "PropertyValue", 
        "value": [
          "pub.1113181816"
        ]
      }, 
      {
        "name": "nlm_unique_id", 
        "type": "PropertyValue", 
        "value": [
          "101088682"
        ]
      }, 
      {
        "name": "pubmed_id", 
        "type": "PropertyValue", 
        "value": [
          "30943972"
        ]
      }
    ], 
    "sameAs": [
      "https://doi.org/10.1186/s12911-019-0787-y", 
      "https://app.dimensions.ai/details/publication/pub.1113181816"
    ], 
    "sdDataset": "articles", 
    "sdDatePublished": "2019-04-15T08:59", 
    "sdLicense": "https://scigraph.springernature.com/explorer/license/", 
    "sdPublisher": {
      "name": "Springer Nature - SN SciGraph project", 
      "type": "Organization"
    }, 
    "sdSource": "s3://com-uberresearch-data-dimensions-target-20181106-alternative/cleanup/v134/2549eaecd7973599484d7c17b260dba0a4ecb94b/merge/v9/a6c9fde33151104705d4d7ff012ea9563521a3ce/jats-lookup/v90/0000000375_0000000375/records_91432_00000001.jsonl", 
    "type": "ScholarlyArticle", 
    "url": "https://bmcmedinformdecismak.biomedcentral.com/articles/10.1186/s12911-019-0787-y"
  }
]
 

Download the RDF metadata as:  json-ld nt turtle xml License info

HOW TO GET THIS DATA PROGRAMMATICALLY:

JSON-LD is a popular format for linked data which is fully compatible with JSON.

curl -H 'Accept: application/ld+json' 'https://scigraph.springernature.com/pub.10.1186/s12911-019-0787-y'

N-Triples is a line-based linked data format ideal for batch operations.

curl -H 'Accept: application/n-triples' 'https://scigraph.springernature.com/pub.10.1186/s12911-019-0787-y'

Turtle is a human-readable linked data format.

curl -H 'Accept: text/turtle' 'https://scigraph.springernature.com/pub.10.1186/s12911-019-0787-y'

RDF/XML is a standard XML format for linked data.

curl -H 'Accept: application/rdf+xml' 'https://scigraph.springernature.com/pub.10.1186/s12911-019-0787-y'


 

This table displays all metadata directly associated to this object as RDF triples.

114 TRIPLES      21 PREDICATES      37 URIs      20 LITERALS      8 BLANK NODES

Subject Predicate Object
1 sg:pub.10.1186/s12911-019-0787-y schema:about anzsrc-for:08
2 anzsrc-for:0801
3 schema:author N72b9930febd64e15a6296bc83e4cdf62
4 schema:citation sg:pub.10.1007/978-3-642-40802-1_24
5 sg:pub.10.1186/s12859-017-1476-4
6 sg:pub.10.1186/s12911-017-0468-7
7 https://doi.org/10.1016/j.jbi.2015.06.007
8 https://doi.org/10.1093/bioinformatics/btx761
9 https://doi.org/10.1136/amiajnl-2013-001628
10 https://doi.org/10.1136/amiajnl-2013-002381
11 https://doi.org/10.1136/jamia.2010.003947
12 https://doi.org/10.18653/v1/s15-2136
13 schema:datePublished 2019-04
14 schema:datePublishedReg 2019-04-01
15 schema:description BACKGROUND: Clinical entity recognition as a fundamental task of clinical text processing has been attracted a great deal of attention during the last decade. However, most studies focus on clinical text in English rather than other languages. Recently, a few researchers have began to study entity recognition in Chinese clinical text. METHODS: In this paper, a novel deep neural network, called attention-based CNN-LSTM-CRF, is proposed to recognize entities in Chinese clinical text. Attention-based CNN-LSTM-CRF is an extension of LSTM-CRF by introducing a CNN (convolutional neural network) layer after the input layer to capture local context information of words of interest and an attention layer before the CRF layer to select relevant words in the same sentence. RESULTS: In order to evaluate the proposed method, we compare it with other two currently popular methods, CRF (conditional random field) and LSTM-CRF, on two benchmark datasets. One of the datasets is publically available and only contains contiguous clinical entities, and the other one is constructed by us and contains contiguous and discontiguous clinical entities. Experimental results show that attention-based CNN-LSTM-CRF outperforms CRF and LSTM-CRF. CONCLUSIONS: CNN and attention mechanism are individually beneficial to LSTM-CRF-based Chinese clinical entity recognition system, no matter whether contiguous clinical entities are considered. The conribution of attention mechanism is greater than CNN.
16 schema:genre research_article
17 schema:inLanguage en
18 schema:isAccessibleForFree true
19 schema:isPartOf N7fc52e6c482047df90c5d17a56a8d7bd
20 Nf0156a1e96a14653a0bcdf3b34b58dbe
21 sg:journal.1028432
22 schema:name Entity recognition in Chinese clinical text using attention-based CNN-LSTM-CRF.
23 schema:pagination 74
24 schema:productId N46517bf3c45c44e584758e68b8786573
25 N502216b1c1264ce5b8bb4c3ed410768d
26 N70595cde3d274dcc9b26e84f46b6dad4
27 N853d4f2a6637442aab63c3c603eb7562
28 schema:sameAs https://app.dimensions.ai/details/publication/pub.1113181816
29 https://doi.org/10.1186/s12911-019-0787-y
30 schema:sdDatePublished 2019-04-15T08:59
31 schema:sdLicense https://scigraph.springernature.com/explorer/license/
32 schema:sdPublisher Ndbd65c1206274b3e9fcb43fb539747ce
33 schema:url https://bmcmedinformdecismak.biomedcentral.com/articles/10.1186/s12911-019-0787-y
34 sgo:license sg:explorer/license/
35 sgo:sdDataset articles
36 rdf:type schema:ScholarlyArticle
37 N0e2cd1ae6a134b8980a3569ec04c8261 schema:affiliation https://www.grid.ac/institutes/grid.19373.3f
38 schema:familyName Wang
39 schema:givenName Xiaolong
40 rdf:type schema:Person
41 N2537bdfd553342f5a9048c0b17c27926 schema:affiliation N4826e34f93564382926dbf7ffe1938c3
42 schema:familyName Yan
43 schema:givenName Jun
44 rdf:type schema:Person
45 N46517bf3c45c44e584758e68b8786573 schema:name dimensions_id
46 schema:value pub.1113181816
47 rdf:type schema:PropertyValue
48 N4826e34f93564382926dbf7ffe1938c3 schema:name Yidu Cloud (Beijing) Technology Co., Ltd, Beijing, 100191, China.
49 rdf:type schema:Organization
50 N502216b1c1264ce5b8bb4c3ed410768d schema:name pubmed_id
51 schema:value 30943972
52 rdf:type schema:PropertyValue
53 N70595cde3d274dcc9b26e84f46b6dad4 schema:name nlm_unique_id
54 schema:value 101088682
55 rdf:type schema:PropertyValue
56 N72b9930febd64e15a6296bc83e4cdf62 rdf:first Nfb9546fbac294b30a825da9251459597
57 rdf:rest Nf2998d24350a4ebc8ecce9979af234a1
58 N7fc52e6c482047df90c5d17a56a8d7bd schema:volumeNumber 19
59 rdf:type schema:PublicationVolume
60 N853d4f2a6637442aab63c3c603eb7562 schema:name doi
61 schema:value 10.1186/s12911-019-0787-y
62 rdf:type schema:PropertyValue
63 Nc5be46a99da2495c8e6b8d6d3bdb8a12 rdf:first Nfe6e1809c4f24e71b379f375c5134c51
64 rdf:rest rdf:nil
65 Nd0a9aae5eb2c4c46ad41a561363c36fe rdf:first N2537bdfd553342f5a9048c0b17c27926
66 rdf:rest Nc5be46a99da2495c8e6b8d6d3bdb8a12
67 Ndbd65c1206274b3e9fcb43fb539747ce schema:name Springer Nature - SN SciGraph project
68 rdf:type schema:Organization
69 Nf0156a1e96a14653a0bcdf3b34b58dbe schema:issueNumber Suppl 3
70 rdf:type schema:PublicationIssue
71 Nf2998d24350a4ebc8ecce9979af234a1 rdf:first N0e2cd1ae6a134b8980a3569ec04c8261
72 rdf:rest Nd0a9aae5eb2c4c46ad41a561363c36fe
73 Nfb9546fbac294b30a825da9251459597 schema:affiliation https://www.grid.ac/institutes/grid.19373.3f
74 schema:familyName Tang
75 schema:givenName Buzhou
76 rdf:type schema:Person
77 Nfe6e1809c4f24e71b379f375c5134c51 schema:affiliation https://www.grid.ac/institutes/grid.19373.3f
78 schema:familyName Chen
79 schema:givenName Qingcai
80 rdf:type schema:Person
81 anzsrc-for:08 schema:inDefinedTermSet anzsrc-for:
82 schema:name Information and Computing Sciences
83 rdf:type schema:DefinedTerm
84 anzsrc-for:0801 schema:inDefinedTermSet anzsrc-for:
85 schema:name Artificial Intelligence and Image Processing
86 rdf:type schema:DefinedTerm
87 sg:journal.1028432 schema:issn 1472-6947
88 schema:name BMC Medical Informatics and Decision Making
89 rdf:type schema:Periodical
90 sg:pub.10.1007/978-3-642-40802-1_24 schema:sameAs https://app.dimensions.ai/details/publication/pub.1043419029
91 https://doi.org/10.1007/978-3-642-40802-1_24
92 rdf:type schema:CreativeWork
93 sg:pub.10.1186/s12859-017-1476-4 schema:sameAs https://app.dimensions.ai/details/publication/pub.1083399581
94 https://doi.org/10.1186/s12859-017-1476-4
95 rdf:type schema:CreativeWork
96 sg:pub.10.1186/s12911-017-0468-7 schema:sameAs https://app.dimensions.ai/details/publication/pub.1090363539
97 https://doi.org/10.1186/s12911-017-0468-7
98 rdf:type schema:CreativeWork
99 https://doi.org/10.1016/j.jbi.2015.06.007 schema:sameAs https://app.dimensions.ai/details/publication/pub.1036391306
100 rdf:type schema:CreativeWork
101 https://doi.org/10.1093/bioinformatics/btx761 schema:sameAs https://app.dimensions.ai/details/publication/pub.1092960287
102 rdf:type schema:CreativeWork
103 https://doi.org/10.1136/amiajnl-2013-001628 schema:sameAs https://app.dimensions.ai/details/publication/pub.1041818540
104 rdf:type schema:CreativeWork
105 https://doi.org/10.1136/amiajnl-2013-002381 schema:sameAs https://app.dimensions.ai/details/publication/pub.1005894580
106 rdf:type schema:CreativeWork
107 https://doi.org/10.1136/jamia.2010.003947 schema:sameAs https://app.dimensions.ai/details/publication/pub.1040096592
108 rdf:type schema:CreativeWork
109 https://doi.org/10.18653/v1/s15-2136 schema:sameAs https://app.dimensions.ai/details/publication/pub.1099096359
110 rdf:type schema:CreativeWork
111 https://www.grid.ac/institutes/grid.19373.3f schema:alternateName Harbin Institute of Technology
112 schema:name Key Laboratory of Network Oriented Intelligent Computation, Harbin Institute of Technology, (Shenzhen), Shenzhen, 518055, China.
113 Key Laboratory of Network Oriented Intelligent Computation, Harbin Institute of Technology, (Shenzhen), Shenzhen, 518055, China. qingcai.chen@gmail.com.
114 rdf:type schema:Organization
 




Preview window. Press ESC to close (or click here)


...