DMCA
Robust Classification of Rare Queries Using Web Knowledge Search (2007)
| Venue: | 179 ― Proceedings of NTCIR-9 Workshop Meeting |
| Citations: | 68 - 11 self |
BibTeX
@INPROCEEDINGS{Broder07robustclassification,
author = {Andrei Broder and Marcus Fontoura and Evgeniy Gabrilovich and Amruta Joshi and Vanja Josifovski and Tong Zhang},
title = {Robust Classification of Rare Queries Using Web Knowledge Search},
booktitle = {179 ― Proceedings of NTCIR-9 Workshop Meeting},
year = {2007},
pages = {6--9}
}
Share
 |
 |
 |
 |
||
OpenURL
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 en-gine. 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 ad-vertising, we primarily focus on rare queries, which are the hardest from the point of view of machine learning, yet in ag-gregation account for a considerable fraction of search engine traffic. Empirical evaluation confirms that our methodology yields a considerably higher classification accuracy than pre-viously 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.
Keyphrases
robust classification blind feedback technique commercial web search query volume search engine traffic query class web search result machine learning reasonable accuracy user experience practical robust query classification system search ad-vertising rare query considerable fraction ag-gregation account classification accuracy empirical evaluation online ad
