Enhancing biomedical concept extraction using semantic relationship weights

Said Bleik, Wei Xiong, Min Song

Research output: Contribution to journalArticle

Abstract

Scientific publications are often associated with a set of keywords to describe their content. Automating the process of keyword extraction and assignment could be useful in indexing electronic documents and building digital libraries. In this paper we propose a new approach to biomedical Concept Extraction (CE) using semantic features of concept graphs. We represent full-text documents by graphs and map biomedical terms to predefined ontology concepts. We adopt concept relation weights to improve the ranking process of potential key concepts. We perform both objective and human-based subjective evaluations. The results show that using relation weights significantly improves the performance of CE. The results also highlight the subjectivity of the CE procedure as well as of its evaluation.

Original languageEnglish
Pages (from-to)303-321
Number of pages19
JournalInternational Journal of Data Mining and Bioinformatics
Volume7
Issue number3
DOIs
Publication statusPublished - 2013 Apr 29

Fingerprint

Semantics
semantics
Digital Libraries
Weights and Measures
Publications
Digital libraries
Ontology
indexing
evaluation
ontology
subjectivity
ranking
electronics
performance

All Science Journal Classification (ASJC) codes

  • Information Systems
  • Biochemistry, Genetics and Molecular Biology(all)
  • Library and Information Sciences

Cite this

@article{25906b54636f468baab78881838c37ea,
title = "Enhancing biomedical concept extraction using semantic relationship weights",
abstract = "Scientific publications are often associated with a set of keywords to describe their content. Automating the process of keyword extraction and assignment could be useful in indexing electronic documents and building digital libraries. In this paper we propose a new approach to biomedical Concept Extraction (CE) using semantic features of concept graphs. We represent full-text documents by graphs and map biomedical terms to predefined ontology concepts. We adopt concept relation weights to improve the ranking process of potential key concepts. We perform both objective and human-based subjective evaluations. The results show that using relation weights significantly improves the performance of CE. The results also highlight the subjectivity of the CE procedure as well as of its evaluation.",
author = "Said Bleik and Wei Xiong and Min Song",
year = "2013",
month = "4",
day = "29",
doi = "10.1504/IJDMB.2013.053307",
language = "English",
volume = "7",
pages = "303--321",
journal = "International Journal of Data Mining and Bioinformatics",
issn = "1748-5673",
publisher = "Inderscience Enterprises Ltd",
number = "3",

}

Enhancing biomedical concept extraction using semantic relationship weights. / Bleik, Said; Xiong, Wei; Song, Min.

In: International Journal of Data Mining and Bioinformatics, Vol. 7, No. 3, 29.04.2013, p. 303-321.

Research output: Contribution to journalArticle

TY - JOUR

T1 - Enhancing biomedical concept extraction using semantic relationship weights

AU - Bleik, Said

AU - Xiong, Wei

AU - Song, Min

PY - 2013/4/29

Y1 - 2013/4/29

N2 - Scientific publications are often associated with a set of keywords to describe their content. Automating the process of keyword extraction and assignment could be useful in indexing electronic documents and building digital libraries. In this paper we propose a new approach to biomedical Concept Extraction (CE) using semantic features of concept graphs. We represent full-text documents by graphs and map biomedical terms to predefined ontology concepts. We adopt concept relation weights to improve the ranking process of potential key concepts. We perform both objective and human-based subjective evaluations. The results show that using relation weights significantly improves the performance of CE. The results also highlight the subjectivity of the CE procedure as well as of its evaluation.

AB - Scientific publications are often associated with a set of keywords to describe their content. Automating the process of keyword extraction and assignment could be useful in indexing electronic documents and building digital libraries. In this paper we propose a new approach to biomedical Concept Extraction (CE) using semantic features of concept graphs. We represent full-text documents by graphs and map biomedical terms to predefined ontology concepts. We adopt concept relation weights to improve the ranking process of potential key concepts. We perform both objective and human-based subjective evaluations. The results show that using relation weights significantly improves the performance of CE. The results also highlight the subjectivity of the CE procedure as well as of its evaluation.

UR - http://www.scopus.com/inward/record.url?scp=84876540575&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84876540575&partnerID=8YFLogxK

U2 - 10.1504/IJDMB.2013.053307

DO - 10.1504/IJDMB.2013.053307

M3 - Article

C2 - 23819261

AN - SCOPUS:84876540575

VL - 7

SP - 303

EP - 321

JO - International Journal of Data Mining and Bioinformatics

JF - International Journal of Data Mining and Bioinformatics

SN - 1748-5673

IS - 3

ER -