We propose a methodology for building a robust query classification system that can identify thousands of query classes, while dealing in real time with the query volume of a commercial Web search engine. We use a pseudo relevance 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 aggregate 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.
%0 Journal Article
%1 citeulike:4416084
%A Gabrilovich, Evgeniy
%A Broder, Andrei
%A Fontoura, Marcus
%A Joshi, Amruta
%A Josifovski, Vanja
%A Riedel, Lance
%A Zhang, Tong
%C New York, NY, USA
%D 2009
%I ACM
%J ACM Trans. Web
%K advertising, classification, queries
%N 2
%P 1--28
%R 10.1145/1513876.1513877
%T Classifying search queries using the Web as a source of knowledge
%U http://dx.doi.org/10.1145/1513876.1513877
%V 3
%X We propose a methodology for building a robust query classification system that can identify thousands of query classes, while dealing in real time with the query volume of a commercial Web search engine. We use a pseudo relevance 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 aggregate 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.
@article{citeulike:4416084,
abstract = {We propose a methodology for building a robust query classification system that can identify thousands of query classes, while dealing in real time with the query volume of a commercial Web search engine. We use a pseudo relevance 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 aggregate 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.},
added-at = {2009-08-06T15:16:38.000+0200},
address = {New York, NY, USA},
author = {Gabrilovich, Evgeniy and Broder, Andrei and Fontoura, Marcus and Joshi, Amruta and Josifovski, Vanja and Riedel, Lance and Zhang, Tong},
biburl = {https://www.bibsonomy.org/bibtex/2f452e04f85379849fc0d6f1c41eeb168/chato},
citeulike-article-id = {4416084},
citeulike-linkout-0 = {http://portal.acm.org/citation.cfm?id=1513876.1513877},
citeulike-linkout-1 = {http://dx.doi.org/10.1145/1513876.1513877},
doi = {10.1145/1513876.1513877},
interhash = {c116d6e62219b6dd1ac4a361b1c322fe},
intrahash = {f452e04f85379849fc0d6f1c41eeb168},
issn = {1559-1131},
journal = {ACM Trans. Web},
keywords = {advertising, classification, queries},
number = 2,
pages = {1--28},
posted-at = {2009-04-28 16:07:46},
priority = {5},
publisher = {ACM},
timestamp = {2009-08-06T15:16:41.000+0200},
title = {Classifying search queries using the Web as a source of knowledge},
url = {http://dx.doi.org/10.1145/1513876.1513877},
volume = 3,
year = 2009
}