Propositional term extraction over short text using word cohesiveness and conditional random fields with multi-level features

Ru Yng Chang, Chung-Hsien Wu

研究成果: Paper

摘要

Propositional terms in a research abstract (RA) generally convey the most important information for readers to quickly glean the contribution of a research article. This paper considers propositional term extraction from RAs as a sequence labeling task using the IOB (Inside, Outside, Beginning) encoding scheme. In this study, conditional random fields (CRFs) are used to initially detect the propositional terms, and the combined association measure (CAM) is applied to further adjust the term boundaries. This method can extract beyond simply NP-based propositional terms by combining multi-level features and inner lexical cohesion. Experimental results show that CRFs can significantly increase the recall rate of imperfect boundary term extraction and the CAM can further effectively improve the term boundaries.

原文English
頁面151-165
頁數15
出版狀態Published - 2008 十二月 1
事件20th Conference on Computational Linguistics and Speech Processing, ROCLING 2008 - Taipei, Taiwan
持續時間: 2008 九月 42008 九月 5

Other

Other20th Conference on Computational Linguistics and Speech Processing, ROCLING 2008
國家Taiwan
城市Taipei
期間08-09-0408-09-05

指紋

Research
Term Extraction
Labeling
Imperfect
Encoding
Reader
Research Articles
Lexical Cohesion

All Science Journal Classification (ASJC) codes

  • Language and Linguistics
  • Speech and Hearing

引用此文

Chang, R. Y., & Wu, C-H. (2008). Propositional term extraction over short text using word cohesiveness and conditional random fields with multi-level features. 151-165. 論文發表於 20th Conference on Computational Linguistics and Speech Processing, ROCLING 2008, Taipei, Taiwan.
Chang, Ru Yng ; Wu, Chung-Hsien. / Propositional term extraction over short text using word cohesiveness and conditional random fields with multi-level features. 論文發表於 20th Conference on Computational Linguistics and Speech Processing, ROCLING 2008, Taipei, Taiwan.15 p.
@conference{f06d4897c6e44715a4b127fafa5112e9,
title = "Propositional term extraction over short text using word cohesiveness and conditional random fields with multi-level features",
abstract = "Propositional terms in a research abstract (RA) generally convey the most important information for readers to quickly glean the contribution of a research article. This paper considers propositional term extraction from RAs as a sequence labeling task using the IOB (Inside, Outside, Beginning) encoding scheme. In this study, conditional random fields (CRFs) are used to initially detect the propositional terms, and the combined association measure (CAM) is applied to further adjust the term boundaries. This method can extract beyond simply NP-based propositional terms by combining multi-level features and inner lexical cohesion. Experimental results show that CRFs can significantly increase the recall rate of imperfect boundary term extraction and the CAM can further effectively improve the term boundaries.",
author = "Chang, {Ru Yng} and Chung-Hsien Wu",
year = "2008",
month = "12",
day = "1",
language = "English",
pages = "151--165",
note = "20th Conference on Computational Linguistics and Speech Processing, ROCLING 2008 ; Conference date: 04-09-2008 Through 05-09-2008",

}

Chang, RY & Wu, C-H 2008, 'Propositional term extraction over short text using word cohesiveness and conditional random fields with multi-level features', 論文發表於 20th Conference on Computational Linguistics and Speech Processing, ROCLING 2008, Taipei, Taiwan, 08-09-04 - 08-09-05 頁 151-165.

Propositional term extraction over short text using word cohesiveness and conditional random fields with multi-level features. / Chang, Ru Yng; Wu, Chung-Hsien.

2008. 151-165 論文發表於 20th Conference on Computational Linguistics and Speech Processing, ROCLING 2008, Taipei, Taiwan.

研究成果: Paper

TY - CONF

T1 - Propositional term extraction over short text using word cohesiveness and conditional random fields with multi-level features

AU - Chang, Ru Yng

AU - Wu, Chung-Hsien

PY - 2008/12/1

Y1 - 2008/12/1

N2 - Propositional terms in a research abstract (RA) generally convey the most important information for readers to quickly glean the contribution of a research article. This paper considers propositional term extraction from RAs as a sequence labeling task using the IOB (Inside, Outside, Beginning) encoding scheme. In this study, conditional random fields (CRFs) are used to initially detect the propositional terms, and the combined association measure (CAM) is applied to further adjust the term boundaries. This method can extract beyond simply NP-based propositional terms by combining multi-level features and inner lexical cohesion. Experimental results show that CRFs can significantly increase the recall rate of imperfect boundary term extraction and the CAM can further effectively improve the term boundaries.

AB - Propositional terms in a research abstract (RA) generally convey the most important information for readers to quickly glean the contribution of a research article. This paper considers propositional term extraction from RAs as a sequence labeling task using the IOB (Inside, Outside, Beginning) encoding scheme. In this study, conditional random fields (CRFs) are used to initially detect the propositional terms, and the combined association measure (CAM) is applied to further adjust the term boundaries. This method can extract beyond simply NP-based propositional terms by combining multi-level features and inner lexical cohesion. Experimental results show that CRFs can significantly increase the recall rate of imperfect boundary term extraction and the CAM can further effectively improve the term boundaries.

UR - http://www.scopus.com/inward/record.url?scp=84883111666&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84883111666&partnerID=8YFLogxK

M3 - Paper

AN - SCOPUS:84883111666

SP - 151

EP - 165

ER -

Chang RY, Wu C-H. Propositional term extraction over short text using word cohesiveness and conditional random fields with multi-level features. 2008. 論文發表於 20th Conference on Computational Linguistics and Speech Processing, ROCLING 2008, Taipei, Taiwan.