Abstract：In information retrieval, relevance feedback is an effective way to improve retrieval performance. The goal is to input user's judgement on previous retrieved documents, and to select some terms for query expansion using certain strategy. This paper introduces some common query expansion approaches in relevance feedback based on probability model and vector space model, then a new term selection method is introduced based on language model,which takes into account two features of expanded terms - "relevance" and "coverage". The evaluation is conducted on the TREC Collection, which shows that our method is better than traditional ones on average precision.
[1] Ming Zhang , Ruihua Song , Chuan Lin , et al . Expansion-Based Techologies in Finding Relevant and New information[A]. TREC 2002 [C]. [2] 贺宏朝,何丕廉,等. 一种基于上下文的中文信息检索查询扩展[J]. 中文信息学报, 2002, 16 (6) : 32 - 37. [3] Rocchio, J. J. Relevant Feedback in Information Retrieval [M] , Chapter 14, pages 313 - 323. Prentice - Hall Inc. 1971. [4] Maron M. E. , Kuhns J. L. On Relevance, Probabilistic Indexing and Information Retrieva1 [J]. Journal of the Association for Computer Machinery. 1960, 7: 216 - 244. [5] Rocchio J. J. Relevance Feedback in Information Retrieva1. In Salton G. (Ed.) , The SMART Retrieval System [M]. 1971. Engle-wood CIifs, Prentice-Hall, Inc. 3l3 - 323. [6] S E Robertson , S Walker , M Beaulieu . Okap i at TREC27: automatic ad hoc, filtering ,VLC and interactive [A]. TREC - 7 [C]. [7] S E Robertson and SWalker. Okap i/Keenbow at TREC28. TREC28 [C]. [8] S E Robertson and K. Sparck Jones. Relevance Weighting of Searching Terms[J]. Journal of the American Society for Information Sciences. 1976, 27 (3) : 129 - 146. [9] S E Robertson. On term selection for query expansion. Journal of Documentation [J]. 1990, 46: 359 - 364. [10] J. M. Ponte and W. B. Croft. A Language modeling approach to IR [A]. In: proceedings of the ACM SIGIR Conference [C]. 1998, 275 - 281. [11] C. Zhai and J. Lafferty. A study of smoothing methods for language models applied to ad hoc information retrieval[A]. In: proceedings of the ACM-SIGIR 2001 [C]. 334 - 342.
2006, Vol. 20 
