A hybrid abbreviation extraction technique for biomedical literature

Min Song, Illhoi Yoo

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Abstract

In this paper, we propose a novel technique to extract abbreviation combining natural language processing techniques and the Support Vector Machine (SVM) in biomedical literature. The proposed technique gives us the comparative advantages over others in the following aspects: 1) It incorporates lexical analysis techniques to supervised learning for extracting abbreviations. 2) It makes use of text chunking techniques to identify long forms of abbreviations. 3) It significantly improves Recall compared to other techniques. The experimental results show that our approach outperforms the leading abbreviation algorithms, ExtractAbbrev, ALICE, and Acrophile, at least by 6%, 13.9%, and 13.2% respectively, in both Precision and Recall on the Gold Standard Development corpus.

Original languageEnglish
Title of host publicationProceedings - 2007 IEEE International Conference on Bioinformatics and Biomedicine, BIBM 2007
Pages42-47
Number of pages6
DOIs
Publication statusPublished - 2007 Dec 1
Event2007 IEEE International Conference on Bioinformatics and Biomedicine, BIBM 2007 - Fremont, CA, United States
Duration: 2007 Nov 22007 Nov 4

Other

Other2007 IEEE International Conference on Bioinformatics and Biomedicine, BIBM 2007
CountryUnited States
CityFremont, CA
Period07/11/207/11/4

Fingerprint

Natural Language Processing
Supervised learning
Support vector machines
Learning
Processing
Support Vector Machine

All Science Journal Classification (ASJC) codes

  • Biotechnology
  • Computer Science(all)
  • Biomedical Engineering

Cite this

Song, M., & Yoo, I. (2007). A hybrid abbreviation extraction technique for biomedical literature. In Proceedings - 2007 IEEE International Conference on Bioinformatics and Biomedicine, BIBM 2007 (pp. 42-47). [4413035] https://doi.org/10.1109/BIBM.2007.33
Song, Min ; Yoo, Illhoi. / A hybrid abbreviation extraction technique for biomedical literature. Proceedings - 2007 IEEE International Conference on Bioinformatics and Biomedicine, BIBM 2007. 2007. pp. 42-47
@inproceedings{0a2cbaccf8af45fb8250f1f4dea436f0,
title = "A hybrid abbreviation extraction technique for biomedical literature",
abstract = "In this paper, we propose a novel technique to extract abbreviation combining natural language processing techniques and the Support Vector Machine (SVM) in biomedical literature. The proposed technique gives us the comparative advantages over others in the following aspects: 1) It incorporates lexical analysis techniques to supervised learning for extracting abbreviations. 2) It makes use of text chunking techniques to identify long forms of abbreviations. 3) It significantly improves Recall compared to other techniques. The experimental results show that our approach outperforms the leading abbreviation algorithms, ExtractAbbrev, ALICE, and Acrophile, at least by 6{\%}, 13.9{\%}, and 13.2{\%} respectively, in both Precision and Recall on the Gold Standard Development corpus.",
author = "Min Song and Illhoi Yoo",
year = "2007",
month = "12",
day = "1",
doi = "10.1109/BIBM.2007.33",
language = "English",
isbn = "0769530311",
pages = "42--47",
booktitle = "Proceedings - 2007 IEEE International Conference on Bioinformatics and Biomedicine, BIBM 2007",

}

Song, M & Yoo, I 2007, A hybrid abbreviation extraction technique for biomedical literature. in Proceedings - 2007 IEEE International Conference on Bioinformatics and Biomedicine, BIBM 2007., 4413035, pp. 42-47, 2007 IEEE International Conference on Bioinformatics and Biomedicine, BIBM 2007, Fremont, CA, United States, 07/11/2. https://doi.org/10.1109/BIBM.2007.33

A hybrid abbreviation extraction technique for biomedical literature. / Song, Min; Yoo, Illhoi.

Proceedings - 2007 IEEE International Conference on Bioinformatics and Biomedicine, BIBM 2007. 2007. p. 42-47 4413035.

Research output: Chapter in Book/Report/Conference proceedingConference contribution

TY - GEN

T1 - A hybrid abbreviation extraction technique for biomedical literature

AU - Song, Min

AU - Yoo, Illhoi

PY - 2007/12/1

Y1 - 2007/12/1

N2 - In this paper, we propose a novel technique to extract abbreviation combining natural language processing techniques and the Support Vector Machine (SVM) in biomedical literature. The proposed technique gives us the comparative advantages over others in the following aspects: 1) It incorporates lexical analysis techniques to supervised learning for extracting abbreviations. 2) It makes use of text chunking techniques to identify long forms of abbreviations. 3) It significantly improves Recall compared to other techniques. The experimental results show that our approach outperforms the leading abbreviation algorithms, ExtractAbbrev, ALICE, and Acrophile, at least by 6%, 13.9%, and 13.2% respectively, in both Precision and Recall on the Gold Standard Development corpus.

AB - In this paper, we propose a novel technique to extract abbreviation combining natural language processing techniques and the Support Vector Machine (SVM) in biomedical literature. The proposed technique gives us the comparative advantages over others in the following aspects: 1) It incorporates lexical analysis techniques to supervised learning for extracting abbreviations. 2) It makes use of text chunking techniques to identify long forms of abbreviations. 3) It significantly improves Recall compared to other techniques. The experimental results show that our approach outperforms the leading abbreviation algorithms, ExtractAbbrev, ALICE, and Acrophile, at least by 6%, 13.9%, and 13.2% respectively, in both Precision and Recall on the Gold Standard Development corpus.

UR - http://www.scopus.com/inward/record.url?scp=49049098267&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=49049098267&partnerID=8YFLogxK

U2 - 10.1109/BIBM.2007.33

DO - 10.1109/BIBM.2007.33

M3 - Conference contribution

AN - SCOPUS:49049098267

SN - 0769530311

SN - 9780769530314

SP - 42

EP - 47

BT - Proceedings - 2007 IEEE International Conference on Bioinformatics and Biomedicine, BIBM 2007

ER -

Song M, Yoo I. A hybrid abbreviation extraction technique for biomedical literature. In Proceedings - 2007 IEEE International Conference on Bioinformatics and Biomedicine, BIBM 2007. 2007. p. 42-47. 4413035 https://doi.org/10.1109/BIBM.2007.33