An incremental approach to MEDLINE MeSH indexing

Dongqing Zhu, Dingcheng Li, Ben Carterette, Hongfang D Liu

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

5 Citations (Scopus)

Abstract

As an increasing number of new journal articles being added to the MEDLINE database each year, it becomes imperative to build effective systems that can automatically suggest Medical Subject Headings (MeSH) to reduce effort from human annotators. In this paper, we propose three approaches, one building upon another in an incremental way, to automatic MeSH term suggestion: 1) MetaMap-based labeling, which relies on the MetaMap tool to detect MeSH-related concepts for indexing; 2) Search-based labeling, which builds on MetaMap-based approach and further leverages information retrieval techniques for finding similar articles whose existing annotations are used for MeSH suggestion; 3) LLDA-based labeling, which further trains a multi-label classifier based on MeSH ontology for MeSH candidate list pruning. The evaluation on the BioASQ challenge data shows promising results.

Original languageEnglish (US)
Title of host publicationCEUR Workshop Proceedings
PublisherCEUR-WS
Volume1094
StatePublished - 2013
Event1st Workshop on Bio-Medical Semantic Indexing and Question Answering, BioASQ 2013 - A Post-Conference Workshop of Conference and Labs of the Evaluation Forum 2013, CLEF 2013 - Valencia, Spain
Duration: Sep 27 2013 → …

Other

Other1st Workshop on Bio-Medical Semantic Indexing and Question Answering, BioASQ 2013 - A Post-Conference Workshop of Conference and Labs of the Evaluation Forum 2013, CLEF 2013
CountrySpain
CityValencia
Period9/27/13 → …

Fingerprint

Labeling
Information retrieval
Ontology
Labels
Classifiers

Keywords

  • Biomedical semantic indexing
  • Information retrieval
  • Query formulation
  • Topic modeling

ASJC Scopus subject areas

  • Computer Science(all)

Cite this

Zhu, D., Li, D., Carterette, B., & Liu, H. D. (2013). An incremental approach to MEDLINE MeSH indexing. In CEUR Workshop Proceedings (Vol. 1094). CEUR-WS.

An incremental approach to MEDLINE MeSH indexing. / Zhu, Dongqing; Li, Dingcheng; Carterette, Ben; Liu, Hongfang D.

CEUR Workshop Proceedings. Vol. 1094 CEUR-WS, 2013.

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

Zhu, D, Li, D, Carterette, B & Liu, HD 2013, An incremental approach to MEDLINE MeSH indexing. in CEUR Workshop Proceedings. vol. 1094, CEUR-WS, 1st Workshop on Bio-Medical Semantic Indexing and Question Answering, BioASQ 2013 - A Post-Conference Workshop of Conference and Labs of the Evaluation Forum 2013, CLEF 2013, Valencia, Spain, 9/27/13.
Zhu D, Li D, Carterette B, Liu HD. An incremental approach to MEDLINE MeSH indexing. In CEUR Workshop Proceedings. Vol. 1094. CEUR-WS. 2013
Zhu, Dongqing ; Li, Dingcheng ; Carterette, Ben ; Liu, Hongfang D. / An incremental approach to MEDLINE MeSH indexing. CEUR Workshop Proceedings. Vol. 1094 CEUR-WS, 2013.
@inproceedings{ec1fc9bc9d6b42e8977fb158301f7f2a,
title = "An incremental approach to MEDLINE MeSH indexing",
abstract = "As an increasing number of new journal articles being added to the MEDLINE database each year, it becomes imperative to build effective systems that can automatically suggest Medical Subject Headings (MeSH) to reduce effort from human annotators. In this paper, we propose three approaches, one building upon another in an incremental way, to automatic MeSH term suggestion: 1) MetaMap-based labeling, which relies on the MetaMap tool to detect MeSH-related concepts for indexing; 2) Search-based labeling, which builds on MetaMap-based approach and further leverages information retrieval techniques for finding similar articles whose existing annotations are used for MeSH suggestion; 3) LLDA-based labeling, which further trains a multi-label classifier based on MeSH ontology for MeSH candidate list pruning. The evaluation on the BioASQ challenge data shows promising results.",
keywords = "Biomedical semantic indexing, Information retrieval, Query formulation, Topic modeling",
author = "Dongqing Zhu and Dingcheng Li and Ben Carterette and Liu, {Hongfang D}",
year = "2013",
language = "English (US)",
volume = "1094",
booktitle = "CEUR Workshop Proceedings",
publisher = "CEUR-WS",

}

TY - GEN

T1 - An incremental approach to MEDLINE MeSH indexing

AU - Zhu, Dongqing

AU - Li, Dingcheng

AU - Carterette, Ben

AU - Liu, Hongfang D

PY - 2013

Y1 - 2013

N2 - As an increasing number of new journal articles being added to the MEDLINE database each year, it becomes imperative to build effective systems that can automatically suggest Medical Subject Headings (MeSH) to reduce effort from human annotators. In this paper, we propose three approaches, one building upon another in an incremental way, to automatic MeSH term suggestion: 1) MetaMap-based labeling, which relies on the MetaMap tool to detect MeSH-related concepts for indexing; 2) Search-based labeling, which builds on MetaMap-based approach and further leverages information retrieval techniques for finding similar articles whose existing annotations are used for MeSH suggestion; 3) LLDA-based labeling, which further trains a multi-label classifier based on MeSH ontology for MeSH candidate list pruning. The evaluation on the BioASQ challenge data shows promising results.

AB - As an increasing number of new journal articles being added to the MEDLINE database each year, it becomes imperative to build effective systems that can automatically suggest Medical Subject Headings (MeSH) to reduce effort from human annotators. In this paper, we propose three approaches, one building upon another in an incremental way, to automatic MeSH term suggestion: 1) MetaMap-based labeling, which relies on the MetaMap tool to detect MeSH-related concepts for indexing; 2) Search-based labeling, which builds on MetaMap-based approach and further leverages information retrieval techniques for finding similar articles whose existing annotations are used for MeSH suggestion; 3) LLDA-based labeling, which further trains a multi-label classifier based on MeSH ontology for MeSH candidate list pruning. The evaluation on the BioASQ challenge data shows promising results.

KW - Biomedical semantic indexing

KW - Information retrieval

KW - Query formulation

KW - Topic modeling

UR - http://www.scopus.com/inward/record.url?scp=84923078263&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84923078263&partnerID=8YFLogxK

M3 - Conference contribution

AN - SCOPUS:84923078263

VL - 1094

BT - CEUR Workshop Proceedings

PB - CEUR-WS

ER -