论文信息 - THUIR at NTCIR-10 INTENT-2 Task

THUIR at NTCIR-10 INTENT-2 Task

This paper describes our approaches and results in NTCIR10 INTENT-2 task. In this year, we participate in subtasks for both the Chinese and English topics. We extract subtopics from multiple resources for these topics, and several subtopic clustering and re-ranking methods are proposed in this work. In Document Ranking subtask, we redefine the novelty of a document and use the new definition to re-rank the retrieved documents. Based on the existing diversification methods, we also try to selectively diversify the search results for the given queries, according to the query types determined by our strategies.

[1] Yiqun Liu,et al. Automatic Query Type Identification Based on Click Through Information , 2006, AIRS.

[2] Dekang Lin,et al. An Information-Theoretic Definition of Similarity , 1998, ICML.

[3] Daniel E. Rose,et al. Understanding user goals in web search , 2004, WWW '04.

[4] Tetsuya Sakai,et al. Evaluating diversified search results using per-intent graded relevance , 2011, SIGIR.

[5] Yiqun Liu,et al. THUIR at NTCIR-9 INTENT Task , 2011, NTCIR.

[6] Michael I. Jordan,et al. Latent Dirichlet Allocation , 2001, J. Mach. Learn. Res..

[7] Yiqun Liu,et al. Overview of the NTCIR-10 INTENT-2 Task , 2013, NTCIR.

[8] Andrei Broder,et al. A taxonomy of web search , 2002, SIGF.

[9] Tetsuya Sakai,et al. Microsoft Research Asia at the NTCIR-10 Intent Task , 2013, NTCIR.

[10] Xiaojie Yuan,et al. Are click-through data adequate for learning web search rankings? , 2008, CIKM '08.

[11] Stephen E. Robertson,et al. Okapi at TREC-3 , 1994, TREC.

[12] Proceedings of the 10th NTCIR Conference on Evaluation of Information Access Technologies, NTCIR-10, National Center of Sciences, Tokyo, Japan, June 18-21, 2013 , 2013, NTCIR.

[13] Stephen E. Robertson,et al. Okapi at TREC-4 , 1995, TREC.