Robust classification of rare queries using web knowledge Export

@inproceedings{sigir2007:robust, abstract = {We propose a methodology for building a practical robust query classification system that can identify thousands of query classes with reasonable accuracy, while dealing in real-time with the query volume of a commercial web search engine. We use a blind feedback technique: given a query, we determine its topic by classifying the web search results retrieved by the query. Motivated by the needs of search advertising, we primarily focus on rare queries, which are the hardest from the point of view of machine learning, yet in aggregation account for a considerable fraction of search engine traffic. Empirical evaluation confirms that our methodology yields a considerably higher classification accuracy than previously reported. We believe that the proposed methodology will lead to better matching of online ads to rare queries and overall to a better user experience.}, address = {New York, NY, USA}, author = {Broder, Andrei Z. and Fontoura, Marcus and Gabrilovich, Evgeniy and Joshi, Amruta and Josifovski, Vanja and Zhang, Tong}, booktitle = {SIGIR '07: Proceedings of the 30th annual international ACM SIGIR conference on Research and development in information retrieval}, citeulike-article-id = {2052976}, citeulike-linkout-0 = {http://portal.acm.org/citation.cfm?id=1277783}, citeulike-linkout-1 = {http://dx.doi.org/10.1145/1277741.1277783}, doi = {10.1145/1277741.1277783}, isbn = {978-1-59593-597-7}, keywords = {categorization, query}, location = {Amsterdam, The Netherlands}, pages = {231--238}, posted-at = {2008-10-21 12:14:40}, priority = {5}, publisher = {ACM}, title = {Robust classification of rare queries using web knowledge}, url = {http://dx.doi.org/10.1145/1277741.1277783}, year = {2007} }

TY - CONF ID - sigir2007:robust L3 - citeulike-article-id:2052976 N2 - We propose a methodology for building a practical robust query classification system that can identify thousands of query classes with reasonable accuracy, while dealing in real-time with the query volume of a commercial web search engine. We use a blind feedback technique: given a query, we determine its topic by classifying the web search results retrieved by the query. Motivated by the needs of search advertising, we primarily focus on rare queries, which are the hardest from the point of view of machine learning, yet in aggregation account for a considerable fraction of search engine traffic. Empirical evaluation confirms that our methodology yields a considerably higher classification accuracy than previously reported. We believe that the proposed methodology will lead to better matching of online ads to rare queries and overall to a better user experience. CY - Amsterdam, The Netherlands SN - 978-1-59593-597-7 AD - New York, NY, USA EP - 238 TI - Robust classification of rare queries using web knowledge PB - ACM T2 - SIGIR '07: Proceedings of the 30th annual international ACM SIGIR conference on Research and development in information retrieval SP - 231 KW - categorization KW - query AU - Broder, Andrei AU - Fontoura, Marcus AU - Gabrilovich, Evgeniy AU - Joshi, Amruta AU - Josifovski, Vanja AU - Zhang, Tong PY - 2007/// UR - http://dx.doi.org/10.1145/1277741.1277783 ER -