A Task-based Comparison of Linguistic and Semantic Document Retrieval Methods in the Medical Domain

Mohammad Shafahi, Qing Hu, Hamideh Afsarmanesh, Z. Huang, A.C.M. ten Teije, F.A.H. van Harmelen

Research output: Scientific - peer-reviewArticle

Abstract

Text-based and semantics-based methods are both studied intensively as methods for document retrieval. In order to gain insight in the respective merits of these two approaches, we have performed a controlled experiment where we executed a real-life task using both textbased and semantics-based techniques. To maximise the lessons that we could draw about the two approaches, we have performed an experiment where we used the same task (searching papers from the scientific literature needed for updating a medical guideline), the same test-case (updating the 2004 Dutch national breast-cancer guideline), the same gold standard (the updated 2012 Dutch national breast-cancer guideline) and the same corpus (PubMed). We then performed this task using two different methods: retrieving papers based on keywords (text-based approach) and retrieving papers based on semantic annotations (semantics-based approach). Based on this experiment, we discuss the insights that we gained from this dual set of experiments.
Original languageEnglish
JournalCEUR workshop proceedings
Volume1613
StatePublished - 2016

Cite this

@article{39ec163cbc9a41078f10c194ebcd2f3e,
title = "A Task-based Comparison of Linguistic and Semantic Document Retrieval Methods in the Medical Domain",
abstract = "Text-based and semantics-based methods are both studied intensively as methods for document retrieval. In order to gain insight in the respective merits of these two approaches, we have performed a controlled experiment where we executed a real-life task using both textbased and semantics-based techniques. To maximise the lessons that we could draw about the two approaches, we have performed an experiment where we used the same task (searching papers from the scientific literature needed for updating a medical guideline), the same test-case (updating the 2004 Dutch national breast-cancer guideline), the same gold standard (the updated 2012 Dutch national breast-cancer guideline) and the same corpus (PubMed). We then performed this task using two different methods: retrieving papers based on keywords (text-based approach) and retrieving papers based on semantic annotations (semantics-based approach). Based on this experiment, we discuss the insights that we gained from this dual set of experiments.",
keywords = "Concept-based search, Document retrieval, Keyword search, Relation-based search, Semantic annotation",
author = "Mohammad Shafahi and Qing Hu and Hamideh Afsarmanesh and Z. Huang and {ten Teije}, A.C.M. and {van Harmelen}, F.A.H.",
year = "2016",
volume = "1613",
journal = "CEUR workshop proceedings",
issn = "1613-0073",
publisher = "CEUR Workshop Proceedings",

}

TY - JOUR

T1 - A Task-based Comparison of Linguistic and Semantic Document Retrieval Methods in the Medical Domain

AU - Shafahi,Mohammad

AU - Hu,Qing

AU - Afsarmanesh,Hamideh

AU - Huang,Z.

AU - ten Teije,A.C.M.

AU - van Harmelen,F.A.H.

PY - 2016

Y1 - 2016

N2 - Text-based and semantics-based methods are both studied intensively as methods for document retrieval. In order to gain insight in the respective merits of these two approaches, we have performed a controlled experiment where we executed a real-life task using both textbased and semantics-based techniques. To maximise the lessons that we could draw about the two approaches, we have performed an experiment where we used the same task (searching papers from the scientific literature needed for updating a medical guideline), the same test-case (updating the 2004 Dutch national breast-cancer guideline), the same gold standard (the updated 2012 Dutch national breast-cancer guideline) and the same corpus (PubMed). We then performed this task using two different methods: retrieving papers based on keywords (text-based approach) and retrieving papers based on semantic annotations (semantics-based approach). Based on this experiment, we discuss the insights that we gained from this dual set of experiments.

AB - Text-based and semantics-based methods are both studied intensively as methods for document retrieval. In order to gain insight in the respective merits of these two approaches, we have performed a controlled experiment where we executed a real-life task using both textbased and semantics-based techniques. To maximise the lessons that we could draw about the two approaches, we have performed an experiment where we used the same task (searching papers from the scientific literature needed for updating a medical guideline), the same test-case (updating the 2004 Dutch national breast-cancer guideline), the same gold standard (the updated 2012 Dutch national breast-cancer guideline) and the same corpus (PubMed). We then performed this task using two different methods: retrieving papers based on keywords (text-based approach) and retrieving papers based on semantic annotations (semantics-based approach). Based on this experiment, we discuss the insights that we gained from this dual set of experiments.

KW - Concept-based search

KW - Document retrieval

KW - Keyword search

KW - Relation-based search

KW - Semantic annotation

UR - http://www.scopus.com/inward/record.url?scp=84977587698&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84977587698&partnerID=8YFLogxK

M3 - Article

VL - 1613

JO - CEUR workshop proceedings

T2 - CEUR workshop proceedings

JF - CEUR workshop proceedings

SN - 1613-0073

ER -