论文信息 - Overview of the TREC 2013 Federated Web Search Track (draft)

Overview of the TREC 2013 Federated Web Search Track (draft)

The goal of the TREC Federated Web Search track is to promote research related to federated search, in a realistic web setting. This overview paper discusses the main results of the FedWeb 2013 track. In this first year of the track, we focused on basic challenges in federated search: (1) resource selection, and (2) results merging. After an overview of the provided data collection and the relevance judgments for the test topics, the participants’ individual results on both tasks are discused, focusing on global trends and promising research directions.

Dong Nguyen | Dolf Trieschnigg | Djoerd Hiemstra | Thomas Demeester

[1] Milad Shokouhi,et al. Federated Search , 2011, Found. Trends Inf. Retr..

[2] David Hawking,et al. Server selection methods in hybrid portal search , 2005, SIGIR '05.

[3] Djoerd Hiemstra,et al. Ranking XPaths for extracting search result records , 2012 .

[4] Moses Charikar,et al. Similarity estimation techniques from rounding algorithms , 2002, STOC '02.

[5] Thomas Demeester,et al. What Snippets Say about Pages in Federated Web Search , 2012, AIRS.

[6] Jaana Kekäläinen,et al. Using graded relevance assessments in IR evaluation , 2002, J. Assoc. Inf. Sci. Technol..

[7] Andrei Z. Broder,et al. Estimating corpus size via queries , 2006, CIKM '06.

[8] Gregory N. Hullender,et al. Learning to rank using gradient descent , 2005, ICML.

[9] Djoerd Hiemstra,et al. SearchResultFinder: federated search made easy , 2013, SIGIR.

[10] Olivier Chapelle,et al. Expected reciprocal rank for graded relevance , 2009, CIKM.

[11] Fernando Diaz,et al. Sources of evidence for vertical selection , 2009, SIGIR.

[12] Fernando Diaz,et al. A Methodology for Evaluating Aggregated Search Results , 2011, ECIR.