Development and evaluation of a triple parser to enable visual searching with a biomedical search engine

Myungjae Kwak, Gondy Augusta Leroy, Mikyung Kim

Research output: Contribution to journalArticle

1 Citation (Scopus)

Abstract

We describe a new biomedical search engine that enables visual searching and utilises predicates instead of phrases. We report on the development and evaluation of the triple parser, the most essential component of the search engine, which extracts the necessary predicates from the biomedical text. Using texts from three biomedical related sites (N = 180), we compared the parser's output with a gold standard independently created by a medical expert. The parser achieved more than 91% precision and recall. Its individual components showed different strengths with Finite State Automata being excellent for achieving high recall, while Support Vector Machines improved the precision.

Original languageEnglish (US)
Pages (from-to)351-367
Number of pages17
JournalInternational Journal of Biomedical Engineering and Technology
Volume10
Issue number4
DOIs
StatePublished - Jan 1 2012
Externally publishedYes

Fingerprint

Search engines
Finite automata
Support vector machines

Keywords

  • Finite State Automata
  • Kernel methods
  • Search engine
  • Support Vector Machines
  • Text mining
  • Triple

ASJC Scopus subject areas

  • Biomedical Engineering

Cite this

Development and evaluation of a triple parser to enable visual searching with a biomedical search engine. / Kwak, Myungjae; Leroy, Gondy Augusta; Kim, Mikyung.

In: International Journal of Biomedical Engineering and Technology, Vol. 10, No. 4, 01.01.2012, p. 351-367.

Research output: Contribution to journalArticle

@article{20cfe7899bd6441fa91ac718ef7abfd4,
title = "Development and evaluation of a triple parser to enable visual searching with a biomedical search engine",
abstract = "We describe a new biomedical search engine that enables visual searching and utilises predicates instead of phrases. We report on the development and evaluation of the triple parser, the most essential component of the search engine, which extracts the necessary predicates from the biomedical text. Using texts from three biomedical related sites (N = 180), we compared the parser's output with a gold standard independently created by a medical expert. The parser achieved more than 91{\%} precision and recall. Its individual components showed different strengths with Finite State Automata being excellent for achieving high recall, while Support Vector Machines improved the precision.",
keywords = "Finite State Automata, Kernel methods, Search engine, Support Vector Machines, Text mining, Triple",
author = "Myungjae Kwak and Leroy, {Gondy Augusta} and Mikyung Kim",
year = "2012",
month = "1",
day = "1",
doi = "10.1504/IJBET.2012.052397",
language = "English (US)",
volume = "10",
pages = "351--367",
journal = "International Journal of Biomedical Engineering and Technology",
issn = "1752-6418",
publisher = "Inderscience Enterprises Ltd",
number = "4",

}

TY - JOUR

T1 - Development and evaluation of a triple parser to enable visual searching with a biomedical search engine

AU - Kwak, Myungjae

AU - Leroy, Gondy Augusta

AU - Kim, Mikyung

PY - 2012/1/1

Y1 - 2012/1/1

N2 - We describe a new biomedical search engine that enables visual searching and utilises predicates instead of phrases. We report on the development and evaluation of the triple parser, the most essential component of the search engine, which extracts the necessary predicates from the biomedical text. Using texts from three biomedical related sites (N = 180), we compared the parser's output with a gold standard independently created by a medical expert. The parser achieved more than 91% precision and recall. Its individual components showed different strengths with Finite State Automata being excellent for achieving high recall, while Support Vector Machines improved the precision.

AB - We describe a new biomedical search engine that enables visual searching and utilises predicates instead of phrases. We report on the development and evaluation of the triple parser, the most essential component of the search engine, which extracts the necessary predicates from the biomedical text. Using texts from three biomedical related sites (N = 180), we compared the parser's output with a gold standard independently created by a medical expert. The parser achieved more than 91% precision and recall. Its individual components showed different strengths with Finite State Automata being excellent for achieving high recall, while Support Vector Machines improved the precision.

KW - Finite State Automata

KW - Kernel methods

KW - Search engine

KW - Support Vector Machines

KW - Text mining

KW - Triple

UR - http://www.scopus.com/inward/record.url?scp=84883796242&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84883796242&partnerID=8YFLogxK

U2 - 10.1504/IJBET.2012.052397

DO - 10.1504/IJBET.2012.052397

M3 - Article

VL - 10

SP - 351

EP - 367

JO - International Journal of Biomedical Engineering and Technology

JF - International Journal of Biomedical Engineering and Technology

SN - 1752-6418

IS - 4

ER -