Incorporating non-relevance information in the estimation of query models

Authors
Publication date 2009
Host editors
  • E.M. Voorhees
  • L.P. Buckland
Book title The seventeenth Text REtrieval Conference (TREC 2008) proceedings
Event 17th Text REtrieval Conference (TREC 2008), Gaithersburg, MD, USA
Publisher Gaithersburg, MD, USA: National Institute of Standards and Technology (NIST)
Organisations
  • Faculty of Science (FNWI) - Informatics Institute (IVI)
Abstract We describe the participation of the University of Amsterdam’s ILPS group in the relevance feedback track at TREC 2008. We introduce a new model which incorporates information from relevant and non-relevant documents to improve the estimation of query models. Our main findings are twofold: (i) in terms of statMAP, a larger number of judged non-relevant documents improves retrieval effectiveness and (ii) on the TREC Terabyte topics, we can effectively replace the estimates on the judged non-relevant documents with estimations on the document collection.
Document type Conference contribution
Language English
Published at http://trec.nist.gov/pubs/trec17/papers/uamsterdam-derijke.rf.rev.pdf
Permalink to this page
Back