Topic based language models for ad hoc information retrieval

L. Azzopardi, M. Girolami, C.J. van Rijsbergen

Research output: Chapter in Book/Report/Conference proceedingConference contribution book

35 Citations (Scopus)
9 Downloads (Pure)

Abstract

We propose a topic based approach to 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.

Original languageEnglish
Title of host publication2004 IEEE International Joint Conference on Neural Networks
Place of PublicationPiscataway, NJ
PublisherIEEE
Pages3281-3286
Number of pages6
ISBN (Print)0780383591
DOIs
Publication statusPublished - 17 Jan 2005
Event2004 IEEE International Joint Conference on Neural Networks - Budapest, Hungary
Duration: 25 Jul 200429 Jul 2004

Conference

Conference2004 IEEE International Joint Conference on Neural Networks
CountryHungary
CityBudapest
Period25/07/0429/07/04

    Fingerprint

Keywords

  • language modelling
  • Information retrieval
  • two stage language model

Cite this

Azzopardi, L., Girolami, M., & van Rijsbergen, C. J. (2005). Topic based language models for ad hoc information retrieval. In 2004 IEEE International Joint Conference on Neural Networks (pp. 3281-3286). Piscataway, NJ: IEEE. https://doi.org/10.1109/IJCNN.2004.1381205