University of Amsterdam and University of Twente at the TREC 2007 Million Query Track
暂无分享,去创建一个
In this paper, we document our submis- sions to the TREC 2007 Million Query track. Our main aim is to compare results of the earlier Ter- abyte tracks to the Million Query track. We sub- mitted a number of runs using different document representations (such as full-text, title-fields, or incoming anchor-texts) to increase pool diversity. The initial results show broad agreement in sys- tem rankings over various measures on topic sets judged at both Terabyte and Million Query tracks, with runs using the full-text index giving superior results on all measures, but also some noteworthy upsets.
[1] Gilad Mishne,et al. Language Models for Searching in Web Corpora , 2004, TREC.
[2] Jaap Kamps. Effective Smoothing for a Terabyte of Text , 2005, TREC.
[3] Jaap Kamps. Experiments with Document and Query Representations for a Terabyte of Text , 2006, TREC.
[4] M. de Rijke,et al. Approaches to Robust and Web Retrieval , 2003, TREC.
[5] Xie Kanglin. Lucene Search Engine , 2007 .