Topic based language models for ad hoc information retrieval

Azzopardi, L., Girolami, M. and Van Rijsbergen, C. (2004) Topic based language models for ad hoc information retrieval. In: IEEE International Joint Conference on Neural Networks., Budapest, 25-29 July 2004, pp. 3281-3286. ISBN 0780383591 (doi:10.1109/IJCNN.2004.1381205)

[img]
Preview
Text
ad_hoc.pdf

479kB

Publisher's URL: http://ieeexplore.ieee.org/xpls/abs_all.jsp?arnumber=1381205&tag=1

Abstract

We propose a topic based approach lo language modelling for ad-hoc Information Retrieval (IR). Many smoothed estimators used for the multinomial query model in IR rely upon the estimated background collection probabilities. In this paper, we propose a topic based language modelling approach, that uses a more informative prior based on the topical content of a document. In our experiments, the proposed model provides comparable IR performance to the standard models, but when combined in a two stage language model, it outperforms all other estimated models.

Item Type:Conference Proceedings
Status:Published
Refereed:Yes
Glasgow Author(s) Enlighten ID:Van Rijsbergen, Professor Cornelis and Azzopardi, Dr Leif and Girolami, Prof Mark
Authors: Azzopardi, L., Girolami, M., and Van Rijsbergen, C.
Subjects:Q Science > QA Mathematics > QA75 Electronic computers. Computer science
College/School:College of Science and Engineering > School of Computing Science
Publisher:Institute of Electrical and Electronics Engineers
ISBN:0780383591
Copyright Holders:Copyright © 2004 Institute of Electrical and Electronics Engineers
First Published:First published in Proceedings IEEE International Joint Conference on Neural Networks
Publisher Policy:Reproduced in accordance with the copyright policy of the publisher

University Staff: Request a correction | Enlighten Editors: Update this record