Inferring query models by computing information flow.

Bruza, P.D.; Song, D.

Abstract

The language modelling approach lo information retrieval can also be used lo compute query models. A query model can be envisaged as an expansion of an initial query. The more prominent query models in the literature have a probabilistic basis. This paper introduces an alternative, non-probabilistic approach to query modelling whereby the strength of information flow is computed between a query Q and a term w. Information flow is a reflection of how strongly w is informationally contained within the query Q. The information flow model is based on Hyperspace Analogue to Language (HAL) vector representations, which reflects the lexical co-occurrence information of terms. Research from cognitive science has demonstrated the cognitive compatibility of HAL representations with human processing. Query models computed from TREC queries by HAL-based information flow are compared experimentally with two probabilistic query language models. Experimental results are provided showing the HAL-based information flow model be superior to query models computed via Markov chains, and seems to be as effective as a probabilistically motivated relevance model.

Citation

BRUZA, P.D. and SONG, D. 2002. Inferring query models by computing information flow. In Proceedings of the 11th Association for Computing Machinery (ACM) international conference on information and knowledge management (CIKM'02), 4-9 November 2002, McLean, USA. New York: ACM [online], pages 260-269. Available from: https://doi.org/10.1145/584792.584837

• Conference Name: 11th Association for Computing Machinery (ACM) international conference on information and knowledge management (CIKM'02)
• Conference Location: McLean, USA
• Start Date: Nov 4, 2002
• End Date: Nov 9, 2002
• Acceptance Date: Nov 4, 2002
• Online Publication Date: Nov 4, 2002
• Publication Date: Nov 4, 2002
• Deposit Date: May 25, 2009
• Publicly Available Date: May 25, 2009
• Publisher: ACM Association for Computing Machinery
• Pages: 260-269
• DOI: https://doi.org/10.1145/584792.584837
• Keywords: Inference; Information flow; Query language modelling
• Public URL: http://hdl.handle.net/10059/343