摘要: Long queries frequently contain many extraneous terms that hinder retrieval of relevant documents. We present techniques to reduce long more effective shorter ones lack those terms. Our work is motivated by the observation perfectly reducing TREC description can lead an average improvement 30% in mean precision. approach involves transforming reduction problem into a learning rank all sub-sets original query (sub-queries) based on their predicted quality, and selecting top sub-query. use various measures quality described literature as features represent sub-queries, train classifier. Replacing with top-ranked sub-query chosen ranker results statistically significant 8% our test sets. Analysis shows well-suited for moderately-performing queries, small set predictors are task ranking sub-queries.
acm.org
core.ac.uk
sci-hub.st 参考文章(27)
Vitor R. Carvalho, Jaime G. Carbonell, William W. Cohen, Jonathan L. Elsas, A Meta-Learning Approach for Robust Rank Learning ,(2008)
James Allan, Giridhar Kumaran, A Case For Shorter Queries, and Helping Users Create Them north american chapter of the association for computational linguistics. pp. 220- 227 ,(2007)
Fidel Cacheda, Iadh Ounis, Vassilis Plachouras, Cornelis Joost van Rijsbergen, University of Glasgow at the Web Track: Dynamic Application of Hyperlink Analysis using the Query Scope. text retrieval conference. pp. 646- 652 ,(2003)
Thomas H. Cormen, Ronald L. Rivest, Charles E. Leiserson, Clifford Stein, Introduction to Algorithms, third edition ,(2009)
Maarten De Rijke, Martha Larson, Jiyin He, Using coherence-based measures to predict query difficulty european conference on information retrieval. pp. 689- 694 ,(2008) , 10.5555/1793274.1793368
Thorsten Joachims, Making large-scale support vector machine learning practical Advances in kernel methods. pp. 169- 184 ,(1999)
Ben He, Iadh Ounis, Inferring Query Performance Using Pre-retrieval Predictors string processing and information retrieval. pp. 43- 54 ,(2004) , 10.1007/978-3-540-30213-1_5
Patrick Hanks, Kenneth Ward Church, Word association norms, mutual information, and lexicography Computational Linguistics. ,vol. 16, pp. 22- 29 ,(1990) , 10.5555/89086.89095
Yohannes Tsegay, Falk Scholer, Ying Zhao, Effective pre-retrieval query performance prediction using similarity and variability evidence european conference on information retrieval. pp. 52- 64 ,(2008) , 10.5555/1793274.1793285
Matthew Lease, James Allan, W. Bruce Croft, Regression Rank: Learning to Meet the Opportunity of Descriptive Queries Lecture Notes in Computer Science. pp. 90- 101 ,(2009) , 10.1007/978-3-642-00958-7_11