H. Zeng, Q. He, Z. Chen, W. Ma, and J. Ma. Proceedings of the 27th Annual International ACM SIGIR Conference on Research and Development in Information Retrieval, page 210--217. New York, NY, USA, ACM, (2004)
DOI: 10.1145/1008992.1009030
Abstract
Organizing Web search results into clusters facilitates users' quick browsing through search results. Traditional clustering techniques are inadequate since they don't generate clusters with highly readable names. In this paper, we reformalize the clustering problem as a salient phrase ranking problem. Given a query and the ranked list of documents (typically a list of titles and snippets) returned by a certain Web search engine, our method first extracts and ranks salient phrases as candidate cluster names, based on a regression model learned from human labeled training data. The documents are assigned to relevant salient phrases to form candidate clusters, and the final clusters are generated by merging these candidate clusters. Experimental results verify our method's feasibility and effectiveness.
%0 Conference Paper
%1 zeng2004learning
%A Zeng, Hua-Jun
%A He, Qi-Cai
%A Chen, Zheng
%A Ma, Wei-Ying
%A Ma, Jinwen
%B Proceedings of the 27th Annual International ACM SIGIR Conference on Research and Development in Information Retrieval
%C New York, NY, USA
%D 2004
%I ACM
%K cluster learning search supervised toread web
%P 210--217
%R 10.1145/1008992.1009030
%T Learning to Cluster Web Search Results
%U http://doi.acm.org/10.1145/1008992.1009030
%X Organizing Web search results into clusters facilitates users' quick browsing through search results. Traditional clustering techniques are inadequate since they don't generate clusters with highly readable names. In this paper, we reformalize the clustering problem as a salient phrase ranking problem. Given a query and the ranked list of documents (typically a list of titles and snippets) returned by a certain Web search engine, our method first extracts and ranks salient phrases as candidate cluster names, based on a regression model learned from human labeled training data. The documents are assigned to relevant salient phrases to form candidate clusters, and the final clusters are generated by merging these candidate clusters. Experimental results verify our method's feasibility and effectiveness.
%@ 1-58113-881-4
@inproceedings{zeng2004learning,
abstract = {Organizing Web search results into clusters facilitates users' quick browsing through search results. Traditional clustering techniques are inadequate since they don't generate clusters with highly readable names. In this paper, we reformalize the clustering problem as a salient phrase ranking problem. Given a query and the ranked list of documents (typically a list of titles and snippets) returned by a certain Web search engine, our method first extracts and ranks salient phrases as candidate cluster names, based on a regression model learned from human labeled training data. The documents are assigned to relevant salient phrases to form candidate clusters, and the final clusters are generated by merging these candidate clusters. Experimental results verify our method's feasibility and effectiveness.},
acmid = {1009030},
added-at = {2014-02-27T08:10:23.000+0100},
address = {New York, NY, USA},
author = {Zeng, Hua-Jun and He, Qi-Cai and Chen, Zheng and Ma, Wei-Ying and Ma, Jinwen},
biburl = {https://www.bibsonomy.org/bibtex/2d4edb324143921f5741234e6cd15f411/jaeschke},
booktitle = {Proceedings of the 27th Annual International ACM SIGIR Conference on Research and Development in Information Retrieval},
doi = {10.1145/1008992.1009030},
interhash = {0081a783aa69274d1ba30c4d67a04201},
intrahash = {d4edb324143921f5741234e6cd15f411},
isbn = {1-58113-881-4},
keywords = {cluster learning search supervised toread web},
location = {Sheffield, United Kingdom},
numpages = {8},
pages = {210--217},
publisher = {ACM},
series = {SIGIR '04},
timestamp = {2014-07-28T15:57:31.000+0200},
title = {Learning to Cluster Web Search Results},
url = {http://doi.acm.org/10.1145/1008992.1009030},
year = 2004
}