Facilitating query decomposition in query language modeling by association rule mining using multiple sliding windows.
Bruza, Peter D.
MetadataShow full item record
SONG, D., HUANG, Q., RUGER, S. and BRUZA, P. D., 2008. Facilitating query decomposition in query language modeling by association rule mining using multiple sliding windows. In: C. MACDONALD, I. OUNIS, V. PLACHOURAS, I. RUTHVEN and R.W. WHITE, eds. Advances in Information Retrieval: 30th European Conference on IR Research, ECIR 2008, Glasgow, UK, March 30-April 3, 2008; Proceedings. Berlin: Springer. pp. 334-345.
This paper presents a novel framework to further advance the recent trend of using query decomposition and high-order term re- lationships in query language modeling, which takes into account terms implicitly associated with di®erent subsets of query terms. Existing ap- proaches, most remarkably the language model based on the Information Flow method are however unable to capture multiple levels of associa- tions and also su®er from a high computational overhead. In this paper, we propose to compute association rules from pseudo feedback docu- ments that are segmented into variable length chunks via multiple sliding windows of di®erent sizes. Extensive experiments have been conducted on various TREC collections and our approach signi¯cantly outperforms a baseline Query Likelihood language model, the Relevance Model and the Information Flow model.