Disease named entity recognition using semisupervised learning and conditional random fields

Nichalin Suakkaphong, Zhu Zhang, Hsinchun Chen

Research output: Contribution to journalArticle

9 Citations (Scopus)

Abstract

Information extraction is an important text-mining task that aims at extracting prespecified types of information from large text collections and making them available in structured representations such as databases. In the biomedical domain, information extraction can be applied to help biologists make the most use of their digital-literature archives. Currently, there are large amounts of biomedical literature that contain rich information about biomedical substances. Extracting such knowledge requires a good named entity recognition technique. In this article, we combine conditional random fields (CRFs), a state-of-the-art sequence-labeling algorithm, with two semisupervised learning techniques, bootstrapping and feature sampling, to recognize disease names from biomedical literature. Two data-processing strategies for each technique also were analyzed: one sequentially processing unlabeled data partitions and another one processing unlabeled data partitions in a round-robin fashion. The experimental results showed the advantage of semisupervised learning techniques given limited labeled training data. Specifically, CRFs with bootstrapping implemented in sequential fashion outperformed strictly supervised CRFs for disease name recognition. The project was supported by NIH/NLM Grant R33 LM07299-01, 2002-2005.

Original languageEnglish (US)
Pages (from-to)727-737
Number of pages11
JournalJournal of the American Society for Information Science and Technology
Volume62
Issue number4
DOIs
StatePublished - Apr 2011

Fingerprint

Disease
learning
Labeling
Sampling
grant
Semi-supervised learning
Conditional random fields
Named entity recognition
literature
Bootstrapping
Information extraction
Data base
Text mining

ASJC Scopus subject areas

  • Software
  • Artificial Intelligence
  • Information Systems
  • Human-Computer Interaction
  • Computer Networks and Communications

Cite this

Disease named entity recognition using semisupervised learning and conditional random fields. / Suakkaphong, Nichalin; Zhang, Zhu; Chen, Hsinchun.

In: Journal of the American Society for Information Science and Technology, Vol. 62, No. 4, 04.2011, p. 727-737.

Research output: Contribution to journalArticle

@article{e27bbb8e89ab4d5997fb3443a7e35be9,
title = "Disease named entity recognition using semisupervised learning and conditional random fields",
abstract = "Information extraction is an important text-mining task that aims at extracting prespecified types of information from large text collections and making them available in structured representations such as databases. In the biomedical domain, information extraction can be applied to help biologists make the most use of their digital-literature archives. Currently, there are large amounts of biomedical literature that contain rich information about biomedical substances. Extracting such knowledge requires a good named entity recognition technique. In this article, we combine conditional random fields (CRFs), a state-of-the-art sequence-labeling algorithm, with two semisupervised learning techniques, bootstrapping and feature sampling, to recognize disease names from biomedical literature. Two data-processing strategies for each technique also were analyzed: one sequentially processing unlabeled data partitions and another one processing unlabeled data partitions in a round-robin fashion. The experimental results showed the advantage of semisupervised learning techniques given limited labeled training data. Specifically, CRFs with bootstrapping implemented in sequential fashion outperformed strictly supervised CRFs for disease name recognition. The project was supported by NIH/NLM Grant R33 LM07299-01, 2002-2005.",
author = "Nichalin Suakkaphong and Zhu Zhang and Hsinchun Chen",
year = "2011",
month = "4",
doi = "10.1002/asi.21488",
language = "English (US)",
volume = "62",
pages = "727--737",
journal = "Journal of the Association for Information Science and Technology",
issn = "2330-1635",
publisher = "John Wiley and Sons Ltd",
number = "4",

}

TY - JOUR

T1 - Disease named entity recognition using semisupervised learning and conditional random fields

AU - Suakkaphong, Nichalin

AU - Zhang, Zhu

AU - Chen, Hsinchun

PY - 2011/4

Y1 - 2011/4

N2 - Information extraction is an important text-mining task that aims at extracting prespecified types of information from large text collections and making them available in structured representations such as databases. In the biomedical domain, information extraction can be applied to help biologists make the most use of their digital-literature archives. Currently, there are large amounts of biomedical literature that contain rich information about biomedical substances. Extracting such knowledge requires a good named entity recognition technique. In this article, we combine conditional random fields (CRFs), a state-of-the-art sequence-labeling algorithm, with two semisupervised learning techniques, bootstrapping and feature sampling, to recognize disease names from biomedical literature. Two data-processing strategies for each technique also were analyzed: one sequentially processing unlabeled data partitions and another one processing unlabeled data partitions in a round-robin fashion. The experimental results showed the advantage of semisupervised learning techniques given limited labeled training data. Specifically, CRFs with bootstrapping implemented in sequential fashion outperformed strictly supervised CRFs for disease name recognition. The project was supported by NIH/NLM Grant R33 LM07299-01, 2002-2005.

AB - Information extraction is an important text-mining task that aims at extracting prespecified types of information from large text collections and making them available in structured representations such as databases. In the biomedical domain, information extraction can be applied to help biologists make the most use of their digital-literature archives. Currently, there are large amounts of biomedical literature that contain rich information about biomedical substances. Extracting such knowledge requires a good named entity recognition technique. In this article, we combine conditional random fields (CRFs), a state-of-the-art sequence-labeling algorithm, with two semisupervised learning techniques, bootstrapping and feature sampling, to recognize disease names from biomedical literature. Two data-processing strategies for each technique also were analyzed: one sequentially processing unlabeled data partitions and another one processing unlabeled data partitions in a round-robin fashion. The experimental results showed the advantage of semisupervised learning techniques given limited labeled training data. Specifically, CRFs with bootstrapping implemented in sequential fashion outperformed strictly supervised CRFs for disease name recognition. The project was supported by NIH/NLM Grant R33 LM07299-01, 2002-2005.

UR - http://www.scopus.com/inward/record.url?scp=79952371294&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=79952371294&partnerID=8YFLogxK

U2 - 10.1002/asi.21488

DO - 10.1002/asi.21488

M3 - Article

VL - 62

SP - 727

EP - 737

JO - Journal of the Association for Information Science and Technology

JF - Journal of the Association for Information Science and Technology

SN - 2330-1635

IS - 4

ER -