LFXtractor

Text chunking for long form detection from biomedical text

Min Song, Hongfang D Liu

Research output: Contribution to journalArticle

Abstract

In this paper, we propose a novel method to detect the corresponding long forms (LFs) of short forms (SFs) from biomedical text. The proposed method is differentiated from others as follows: • it incorporates lexical analysis techniques into supervised learning for extracting abbreviations • it utilises text-chunking techniques to identify LFs of abbreviations • it significantly improves recall. The experimental results show that our approach outperforms the leading abbreviation algorithms, ExtractAbbrev, ALICE and Acrophile and a collocation-based approach at least by 4.8, 6.0, 9.0 and 6.0%, respectively, in both precision and recall on the Gold Standard Development corpus.

Original languageEnglish (US)
Pages (from-to)89-102
Number of pages14
JournalInternational Journal of Functional Informatics and Personalised Medicine
Volume3
Issue number2
DOIs
StatePublished - 2010
Externally publishedYes

Fingerprint

Learning

Keywords

  • Abbreviation extraction
  • Text chunking
  • Text mining

ASJC Scopus subject areas

  • Clinical Neurology

Cite this

@article{3ccbdb6a8b054706b41579ed26b60589,
title = "LFXtractor: Text chunking for long form detection from biomedical text",
abstract = "In this paper, we propose a novel method to detect the corresponding long forms (LFs) of short forms (SFs) from biomedical text. The proposed method is differentiated from others as follows: • it incorporates lexical analysis techniques into supervised learning for extracting abbreviations • it utilises text-chunking techniques to identify LFs of abbreviations • it significantly improves recall. The experimental results show that our approach outperforms the leading abbreviation algorithms, ExtractAbbrev, ALICE and Acrophile and a collocation-based approach at least by 4.8, 6.0, 9.0 and 6.0{\%}, respectively, in both precision and recall on the Gold Standard Development corpus.",
keywords = "Abbreviation extraction, Text chunking, Text mining",
author = "Min Song and Liu, {Hongfang D}",
year = "2010",
doi = "10.1504/IJFIPM.2010.037148",
language = "English (US)",
volume = "3",
pages = "89--102",
journal = "International Journal of Functional Informatics and Personalised Medicine",
issn = "1756-2104",
publisher = "Inderscience Publishers",
number = "2",

}

TY - JOUR

T1 - LFXtractor

T2 - Text chunking for long form detection from biomedical text

AU - Song, Min

AU - Liu, Hongfang D

PY - 2010

Y1 - 2010

N2 - In this paper, we propose a novel method to detect the corresponding long forms (LFs) of short forms (SFs) from biomedical text. The proposed method is differentiated from others as follows: • it incorporates lexical analysis techniques into supervised learning for extracting abbreviations • it utilises text-chunking techniques to identify LFs of abbreviations • it significantly improves recall. The experimental results show that our approach outperforms the leading abbreviation algorithms, ExtractAbbrev, ALICE and Acrophile and a collocation-based approach at least by 4.8, 6.0, 9.0 and 6.0%, respectively, in both precision and recall on the Gold Standard Development corpus.

AB - In this paper, we propose a novel method to detect the corresponding long forms (LFs) of short forms (SFs) from biomedical text. The proposed method is differentiated from others as follows: • it incorporates lexical analysis techniques into supervised learning for extracting abbreviations • it utilises text-chunking techniques to identify LFs of abbreviations • it significantly improves recall. The experimental results show that our approach outperforms the leading abbreviation algorithms, ExtractAbbrev, ALICE and Acrophile and a collocation-based approach at least by 4.8, 6.0, 9.0 and 6.0%, respectively, in both precision and recall on the Gold Standard Development corpus.

KW - Abbreviation extraction

KW - Text chunking

KW - Text mining

UR - http://www.scopus.com/inward/record.url?scp=84874158893&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84874158893&partnerID=8YFLogxK

U2 - 10.1504/IJFIPM.2010.037148

DO - 10.1504/IJFIPM.2010.037148

M3 - Article

VL - 3

SP - 89

EP - 102

JO - International Journal of Functional Informatics and Personalised Medicine

JF - International Journal of Functional Informatics and Personalised Medicine

SN - 1756-2104

IS - 2

ER -