Result identification for biomedical abstracts using conditional random fields

Ryan T.K. Lin; Hong Jei Dai; Yue Yang Bow; Min Yuh Day; Richard Tzong Han Tsai; Wen Lian Hsu

doi:10.1109/IRI.2008.4583016

Result identification for biomedical abstracts using conditional random fields

Ryan T.K. Lin, Hong Jei Dai, Yue Yang Bow, Min Yuh Day, Richard Tzong Han Tsai, Wen Lian Hsu

Department of Computer Science and Information Engineering

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

4 Scopus citations

Abstract

For biomedical research, the most important parts of an abstract are the result and conclusion sections. Some journals divide an abstract into several sections so that readers can easily identify those parts, but others do not. We propose a method that can automatically identify the result and conclusion sections of any biomedical abstracts by formulating this identification problem as a sequence labeling task. Three feature sets (Position, Named Entity, and Word Frequency) are employed with Conditional Random Fields (CRFs) as the underlying machine learning model. Experimental results show that the combination of our proposed feature sets can achieve F-measure, precision, and recall scores of 92.50%, 95.32% and 89.85%, respectively.

Original language	English
Title of host publication	Proceedings - CIS Workshops 2007, 2007 International Conference on Computational Intelligence and Security Workshops, CISW 2007
Pages	122-126
Number of pages	5
DOIs	https://doi.org/10.1109/IRI.2008.4583016
State	Published - 2008
Event	2008 IEEE International Conference on Information Reuse and Integration, IEEE IRI-2008 - Las Vegas, NV, United States Duration: 13 Jul 2008 → 15 Jul 2008

Publication series

Name	2008 IEEE International Conference on Information Reuse and Integration, IEEE IRI-2008

Conference

Conference	2008 IEEE International Conference on Information Reuse and Integration, IEEE IRI-2008
Country/Territory	United States
City	Las Vegas, NV
Period	13/07/08 → 15/07/08

Access to Document

10.1109/IRI.2008.4583016

Cite this

Lin, R. T. K., Dai, H. J., Bow, Y. Y., Day, M. Y., Tsai, R. T. H., & Hsu, W. L. (2008). Result identification for biomedical abstracts using conditional random fields. In Proceedings - CIS Workshops 2007, 2007 International Conference on Computational Intelligence and Security Workshops, CISW 2007 (pp. 122-126). Article 4583016 (2008 IEEE International Conference on Information Reuse and Integration, IEEE IRI-2008). https://doi.org/10.1109/IRI.2008.4583016

Lin, Ryan T.K. ; Dai, Hong Jei ; Bow, Yue Yang et al. / Result identification for biomedical abstracts using conditional random fields. Proceedings - CIS Workshops 2007, 2007 International Conference on Computational Intelligence and Security Workshops, CISW 2007. 2008. pp. 122-126 (2008 IEEE International Conference on Information Reuse and Integration, IEEE IRI-2008).

@inproceedings{a422b6a88d33480889038cbede474e33,

title = "Result identification for biomedical abstracts using conditional random fields",

abstract = "For biomedical research, the most important parts of an abstract are the result and conclusion sections. Some journals divide an abstract into several sections so that readers can easily identify those parts, but others do not. We propose a method that can automatically identify the result and conclusion sections of any biomedical abstracts by formulating this identification problem as a sequence labeling task. Three feature sets (Position, Named Entity, and Word Frequency) are employed with Conditional Random Fields (CRFs) as the underlying machine learning model. Experimental results show that the combination of our proposed feature sets can achieve F-measure, precision, and recall scores of 92.50%, 95.32% and 89.85%, respectively.",

author = "Lin, {Ryan T.K.} and Dai, {Hong Jei} and Bow, {Yue Yang} and Day, {Min Yuh} and Tsai, {Richard Tzong Han} and Hsu, {Wen Lian}",

year = "2008",

doi = "10.1109/IRI.2008.4583016",

language = "???core.languages.en_GB???",

isbn = "9781424426607",

series = "2008 IEEE International Conference on Information Reuse and Integration, IEEE IRI-2008",

pages = "122--126",

booktitle = "Proceedings - CIS Workshops 2007, 2007 International Conference on Computational Intelligence and Security Workshops, CISW 2007",

note = "2008 IEEE International Conference on Information Reuse and Integration, IEEE IRI-2008 ; Conference date: 13-07-2008 Through 15-07-2008",

}

Lin, RTK, Dai, HJ, Bow, YY, Day, MY, Tsai, RTH & Hsu, WL 2008, Result identification for biomedical abstracts using conditional random fields. in Proceedings - CIS Workshops 2007, 2007 International Conference on Computational Intelligence and Security Workshops, CISW 2007., 4583016, 2008 IEEE International Conference on Information Reuse and Integration, IEEE IRI-2008, pp. 122-126, 2008 IEEE International Conference on Information Reuse and Integration, IEEE IRI-2008, Las Vegas, NV, United States, 13/07/08. https://doi.org/10.1109/IRI.2008.4583016

Result identification for biomedical abstracts using conditional random fields. / Lin, Ryan T.K.; Dai, Hong Jei; Bow, Yue Yang et al.
Proceedings - CIS Workshops 2007, 2007 International Conference on Computational Intelligence and Security Workshops, CISW 2007. 2008. p. 122-126 4583016 (2008 IEEE International Conference on Information Reuse and Integration, IEEE IRI-2008).

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

TY - GEN

T1 - Result identification for biomedical abstracts using conditional random fields

AU - Lin, Ryan T.K.

AU - Dai, Hong Jei

AU - Bow, Yue Yang

AU - Day, Min Yuh

AU - Tsai, Richard Tzong Han

AU - Hsu, Wen Lian

PY - 2008

Y1 - 2008

N2 - For biomedical research, the most important parts of an abstract are the result and conclusion sections. Some journals divide an abstract into several sections so that readers can easily identify those parts, but others do not. We propose a method that can automatically identify the result and conclusion sections of any biomedical abstracts by formulating this identification problem as a sequence labeling task. Three feature sets (Position, Named Entity, and Word Frequency) are employed with Conditional Random Fields (CRFs) as the underlying machine learning model. Experimental results show that the combination of our proposed feature sets can achieve F-measure, precision, and recall scores of 92.50%, 95.32% and 89.85%, respectively.

AB - For biomedical research, the most important parts of an abstract are the result and conclusion sections. Some journals divide an abstract into several sections so that readers can easily identify those parts, but others do not. We propose a method that can automatically identify the result and conclusion sections of any biomedical abstracts by formulating this identification problem as a sequence labeling task. Three feature sets (Position, Named Entity, and Word Frequency) are employed with Conditional Random Fields (CRFs) as the underlying machine learning model. Experimental results show that the combination of our proposed feature sets can achieve F-measure, precision, and recall scores of 92.50%, 95.32% and 89.85%, respectively.

UR - http://www.scopus.com/inward/record.url?scp=52349109784&partnerID=8YFLogxK

U2 - 10.1109/IRI.2008.4583016

DO - 10.1109/IRI.2008.4583016

M3 - 會議論文篇章

AN - SCOPUS:52349109784

SN - 9781424426607

T3 - 2008 IEEE International Conference on Information Reuse and Integration, IEEE IRI-2008

SP - 122

EP - 126

BT - Proceedings - CIS Workshops 2007, 2007 International Conference on Computational Intelligence and Security Workshops, CISW 2007

T2 - 2008 IEEE International Conference on Information Reuse and Integration, IEEE IRI-2008

Y2 - 13 July 2008 through 15 July 2008

ER -

Lin RTK, Dai HJ, Bow YY, Day MY, Tsai RTH, Hsu WL. Result identification for biomedical abstracts using conditional random fields. In Proceedings - CIS Workshops 2007, 2007 International Conference on Computational Intelligence and Security Workshops, CISW 2007. 2008. p. 122-126. 4583016. (2008 IEEE International Conference on Information Reuse and Integration, IEEE IRI-2008). doi: 10.1109/IRI.2008.4583016

Result identification for biomedical abstracts using conditional random fields

Abstract

Publication series

Conference

Access to Document

Fingerprint

Cite this