Abbreviation definition identification based on automatic precision estimates

Sunghwan Sohn, Donald C. Comeau, Won Kim, John W. Wilbur

Research output: Contribution to journalArticle

37 Citations (Scopus)

Abstract

Background: The rapid growth of biomedical literature presents challenges for automatic text processing, and one of the challenges is abbreviation identification. The presence of unrecognized abbreviations in text hinders indexing algorithms and adversely affects information retrieval and extraction. Automatic abbreviation definition identification can help resolve these issues. However, abbreviations and their definitions identified by an automatic process are of uncertain validity. Due to the size of databases such as MEDLINE only a small fraction of abbreviation-definition pairs can be examined manually. An automatic way to estimate the accuracy of abbreviation-definition pairs extracted from text is needed. In this paper we propose an abbreviation definition identification algorithm that employs a variety of strategies to identify the most probable abbreviation definition. In addition our algorithm produces an accuracy estimate, pseudo-precision, for each strategy without using a human-judged gold standard. The pseudo-precisions determine the order in which the algorithm applies the strategies in seeking to identify the definition of an abbreviation. Results: On the Medstract corpus our algorithm produced 97% precision and 85% recall which is higher than previously reported results. We also annotated 1250 randomly selected MEDLINE records as a gold standard. On this set we achieved 96.5% precision and 83.2% recall. This compares favourably with the well known Schwartz and Hearst algorithm. Conclusion: We developed an algorithm for abbreviation identification that uses a variety of strategies to identify the most probable definition for an abbreviation and also produces an estimated accuracy of the result. This process is purely automatic.

Original languageEnglish (US)
Article number402
JournalBMC Bioinformatics
Volume9
DOIs
StatePublished - Sep 25 2008
Externally publishedYes

Fingerprint

Abbreviation
Estimate
Information Storage and Retrieval
MEDLINE
Text processing
Probable
Gold
Information retrieval
Text Indexing
Text Processing
Databases
Information Extraction
Information Retrieval
Resolve
Growth

ASJC Scopus subject areas

  • Structural Biology
  • Biochemistry
  • Molecular Biology
  • Computer Science Applications
  • Applied Mathematics

Cite this

Abbreviation definition identification based on automatic precision estimates. / Sohn, Sunghwan; Comeau, Donald C.; Kim, Won; Wilbur, John W.

In: BMC Bioinformatics, Vol. 9, 402, 25.09.2008.

Research output: Contribution to journalArticle

Sohn, Sunghwan ; Comeau, Donald C. ; Kim, Won ; Wilbur, John W. / Abbreviation definition identification based on automatic precision estimates. In: BMC Bioinformatics. 2008 ; Vol. 9.
@article{7d30327c5e0740b38a4e7efb04f126da,
title = "Abbreviation definition identification based on automatic precision estimates",
abstract = "Background: The rapid growth of biomedical literature presents challenges for automatic text processing, and one of the challenges is abbreviation identification. The presence of unrecognized abbreviations in text hinders indexing algorithms and adversely affects information retrieval and extraction. Automatic abbreviation definition identification can help resolve these issues. However, abbreviations and their definitions identified by an automatic process are of uncertain validity. Due to the size of databases such as MEDLINE only a small fraction of abbreviation-definition pairs can be examined manually. An automatic way to estimate the accuracy of abbreviation-definition pairs extracted from text is needed. In this paper we propose an abbreviation definition identification algorithm that employs a variety of strategies to identify the most probable abbreviation definition. In addition our algorithm produces an accuracy estimate, pseudo-precision, for each strategy without using a human-judged gold standard. The pseudo-precisions determine the order in which the algorithm applies the strategies in seeking to identify the definition of an abbreviation. Results: On the Medstract corpus our algorithm produced 97{\%} precision and 85{\%} recall which is higher than previously reported results. We also annotated 1250 randomly selected MEDLINE records as a gold standard. On this set we achieved 96.5{\%} precision and 83.2{\%} recall. This compares favourably with the well known Schwartz and Hearst algorithm. Conclusion: We developed an algorithm for abbreviation identification that uses a variety of strategies to identify the most probable definition for an abbreviation and also produces an estimated accuracy of the result. This process is purely automatic.",
author = "Sunghwan Sohn and Comeau, {Donald C.} and Won Kim and Wilbur, {John W.}",
year = "2008",
month = "9",
day = "25",
doi = "10.1186/1471-2105-9-402",
language = "English (US)",
volume = "9",
journal = "BMC Bioinformatics",
issn = "1471-2105",
publisher = "BioMed Central",

}

TY - JOUR

T1 - Abbreviation definition identification based on automatic precision estimates

AU - Sohn, Sunghwan

AU - Comeau, Donald C.

AU - Kim, Won

AU - Wilbur, John W.

PY - 2008/9/25

Y1 - 2008/9/25

N2 - Background: The rapid growth of biomedical literature presents challenges for automatic text processing, and one of the challenges is abbreviation identification. The presence of unrecognized abbreviations in text hinders indexing algorithms and adversely affects information retrieval and extraction. Automatic abbreviation definition identification can help resolve these issues. However, abbreviations and their definitions identified by an automatic process are of uncertain validity. Due to the size of databases such as MEDLINE only a small fraction of abbreviation-definition pairs can be examined manually. An automatic way to estimate the accuracy of abbreviation-definition pairs extracted from text is needed. In this paper we propose an abbreviation definition identification algorithm that employs a variety of strategies to identify the most probable abbreviation definition. In addition our algorithm produces an accuracy estimate, pseudo-precision, for each strategy without using a human-judged gold standard. The pseudo-precisions determine the order in which the algorithm applies the strategies in seeking to identify the definition of an abbreviation. Results: On the Medstract corpus our algorithm produced 97% precision and 85% recall which is higher than previously reported results. We also annotated 1250 randomly selected MEDLINE records as a gold standard. On this set we achieved 96.5% precision and 83.2% recall. This compares favourably with the well known Schwartz and Hearst algorithm. Conclusion: We developed an algorithm for abbreviation identification that uses a variety of strategies to identify the most probable definition for an abbreviation and also produces an estimated accuracy of the result. This process is purely automatic.

AB - Background: The rapid growth of biomedical literature presents challenges for automatic text processing, and one of the challenges is abbreviation identification. The presence of unrecognized abbreviations in text hinders indexing algorithms and adversely affects information retrieval and extraction. Automatic abbreviation definition identification can help resolve these issues. However, abbreviations and their definitions identified by an automatic process are of uncertain validity. Due to the size of databases such as MEDLINE only a small fraction of abbreviation-definition pairs can be examined manually. An automatic way to estimate the accuracy of abbreviation-definition pairs extracted from text is needed. In this paper we propose an abbreviation definition identification algorithm that employs a variety of strategies to identify the most probable abbreviation definition. In addition our algorithm produces an accuracy estimate, pseudo-precision, for each strategy without using a human-judged gold standard. The pseudo-precisions determine the order in which the algorithm applies the strategies in seeking to identify the definition of an abbreviation. Results: On the Medstract corpus our algorithm produced 97% precision and 85% recall which is higher than previously reported results. We also annotated 1250 randomly selected MEDLINE records as a gold standard. On this set we achieved 96.5% precision and 83.2% recall. This compares favourably with the well known Schwartz and Hearst algorithm. Conclusion: We developed an algorithm for abbreviation identification that uses a variety of strategies to identify the most probable definition for an abbreviation and also produces an estimated accuracy of the result. This process is purely automatic.

UR - http://www.scopus.com/inward/record.url?scp=55249111767&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=55249111767&partnerID=8YFLogxK

U2 - 10.1186/1471-2105-9-402

DO - 10.1186/1471-2105-9-402

M3 - Article

VL - 9

JO - BMC Bioinformatics

JF - BMC Bioinformatics

SN - 1471-2105

M1 - 402

ER -