Record Details

On improving Pseudo-relevance feedback using Pseudo-irrelevant documents

DSpace at IIT Bombay

View Archive Info
 
 
Field Value
 
Title On improving Pseudo-relevance feedback using Pseudo-irrelevant documents
 
Creator RAMAN, K
UDUPA, R
BHATTACHARYA, P
BHOLE, A
 
Subject information retrieval
pseudo-relevance feedback
query expansion
pseudo-irrelevance
linear classifier
 
Description Pseudo-Relevance Feedback (PRF) assumes that the top-ranking n documents of the initial retrieval are relevant and extracts expansion terms from them. In this work, we introduce the notion of pseudo-irrelevant documents, i.e. high-scoring documents outside a top n that, are highly unlikely to be relevant. We show how pseudo-irrelevant documents can be used to extract; better expansion terms from the top-ranking n documents: good expansion terms are those which discriminate the top-ranking n documents from the pseudo-irrelevant documents. Our approach gives substantial improvements in retrieval performance over Model-based Feedback on several test collections.
 
Publisher SPRINGER-VERLAG BERLIN
 
Date 2011-10-24T02:26:45Z
2011-12-15T09:11:23Z
2011-10-24T02:26:45Z
2011-12-15T09:11:23Z
2010
 
Type Proceedings Paper
 
Identifier ADVANCES IN INFORMATION RETRIEVAL, PROCEEDINGS,5993,573-576
978-3-642-12274-3
0302-9743
http://dspace.library.iitb.ac.in/xmlui/handle/10054/15307
http://hdl.handle.net/100/2032
 
Source 32nd Europeasn Conference on Information Retrieval Research,Milton Keynes, ENGLAND,MAR 28-31, 2010
 
Language English