Drexel University Home Pagewww.drexel.edu DREXEL UNIVERSITY LIBRARIES HOMEPAGE >>
iDEA DREXEL ARCHIVES >>

iDEA: Drexel E-repository and Archives > Drexel Academic Community > College of Information Science and Technology > Faculty Research and Publications (IST) > Relation-based document retrieval for biomedical IR

Please use this identifier to cite or link to this item: http://hdl.handle.net/1860/1200

Title: Relation-based document retrieval for biomedical IR
Authors: Hu, Xiaohua
Zhou, Xiaohua
Li, Guangren
Lin, Xia
Zhang, Xiaodan
Keywords: Human Papillomavirus Type 11;Organotypic Raft Culture;E1^E4
Issue Date: 9-May-2006
Publisher: Elsevier Science B.V.
Citation: Virology, 351(2): pp. 271-279. http://dx.doi.org/10.1016/j.virol.2006.01.051
Abstract: In this paper, we explore the use of term relations in information retrieval for precision-focused biomedical literature search. A relation is defined as a pair of two terms which are semantically and syntactically related to each other. Unlike the traditional “bag-of-word” model for documents, our model represents a document by a set of sense-disambiguated terms and their binary relations. Since document level co-occurrence of two terms, in many cases, does not mean this document addresses their relationships, the direct use of relation may improve the precision of very specific search, e.g. searching documents that mention genes regulated by Smad4. For this purpose, we develop a generic ontology-based approach to extract terms and their relations, and present a betweenness centrality based approach to rank retrieved documents. A prototyped IR system supporting relation-based search is then built for Medline abstract search. We use this novel IR system to improve the retrieval result of all official runs in TREC-2004 Genomics Track. The experiment shows promising performance of relation-based IR. The average P@100 (the precision of top 100 documents) for 50 topics is significantly raised from 26.37 %( the P@100 of the best run is 42.10%) to 53.69% while the MAP (mean average precision) is kept at an above-average level of 26.59%. The experiment also shows the expressiveness of relations for the representation of information needs, especially in the area of biomedical literature full of various biological relations.
URI: http://hdl.handle.net/1860/1200
Appears in Collections:Faculty Research and Publications (IST)

Files in This Item:

File Description SizeFormat
2006175031.pdf169.08 kBAdobe PDFView/Open
View Statistics

Items in iDEA are protected by copyright, with all rights reserved, unless otherwise indicated.

 

Valid XHTML 1.0! iDEA Software Copyright © 2002-2010  Duraspace - Feedback