Web search engines often federate many user queries to relevant structured databases. For example, a product related query might be federated to a product database containing their descriptions and specifications. The relevant structured data items are then returned to the user along with web search results. However, each structured database is searched in isolation. Hence, the search often produces empty or incomplete results as the database may not contain the required information to answer the query. In this paper, we propose a novel integrated search architecture. We establish and exploit the relationships between web search results and the items in structured databases to identify the relevant structured data items for a much wider range of queries.Our architecture leverages existing search engine components to implement this functionality at very low overhead. We demonstrate the quality and efficiency of our techniques through an extensive experimental study.
%0 Conference Paper
%1 citeulike:4400905
%A Agrawal, Sanjay
%A Chakrabarti, Kaushik
%A Chaudhuri, Surajit
%A Ganti, Venkatesh
%A Konig, Arnd C.
%A Xin, Dong
%B WWW '09: Proceedings of the 18th international conference on World wide web
%C New York, NY, USA
%D 2009
%I ACM
%K databases, search, similarity, text
%P 501--510
%R 10.1145/1526709.1526777
%T Exploiting web search engines to search structured databases
%U http://dx.doi.org/10.1145/1526709.1526777
%X Web search engines often federate many user queries to relevant structured databases. For example, a product related query might be federated to a product database containing their descriptions and specifications. The relevant structured data items are then returned to the user along with web search results. However, each structured database is searched in isolation. Hence, the search often produces empty or incomplete results as the database may not contain the required information to answer the query. In this paper, we propose a novel integrated search architecture. We establish and exploit the relationships between web search results and the items in structured databases to identify the relevant structured data items for a much wider range of queries.Our architecture leverages existing search engine components to implement this functionality at very low overhead. We demonstrate the quality and efficiency of our techniques through an extensive experimental study.
%@ 978-1-60558-487-4
@inproceedings{citeulike:4400905,
abstract = {Web search engines often federate many user queries to relevant structured databases. For example, a product related query might be federated to a product database containing their descriptions and specifications. The relevant structured data items are then returned to the user along with web search results. However, each structured database is searched in isolation. Hence, the search often produces empty or incomplete results as the database may not contain the required information to answer the query. In this paper, we propose a novel integrated search architecture. We establish and exploit the relationships between web search results and the items in structured databases to identify the relevant structured data items for a much wider range of queries.Our architecture leverages existing search engine components to implement this functionality at very low overhead. We demonstrate the quality and efficiency of our techniques through an extensive experimental study.},
added-at = {2009-08-06T15:16:38.000+0200},
address = {New York, NY, USA},
author = {Agrawal, Sanjay and Chakrabarti, Kaushik and Chaudhuri, Surajit and Ganti, Venkatesh and Konig, Arnd C. and Xin, Dong},
biburl = {https://www.bibsonomy.org/bibtex/2215409b2c15b724dbe75647d7b93a0d0/chato},
booktitle = {WWW '09: Proceedings of the 18th international conference on World wide web},
citeulike-article-id = {4400905},
citeulike-linkout-0 = {http://portal.acm.org/citation.cfm?id=1526709.1526777},
citeulike-linkout-1 = {http://dx.doi.org/10.1145/1526709.1526777},
doi = {10.1145/1526709.1526777},
interhash = {95ba72838bd56b5cb399886d8510ff0d},
intrahash = {215409b2c15b724dbe75647d7b93a0d0},
isbn = {978-1-60558-487-4},
keywords = {databases, search, similarity, text},
location = {Madrid, Spain},
pages = {501--510},
posted-at = {2009-04-24 16:30:43},
priority = {0},
publisher = {ACM},
timestamp = {2009-08-06T15:16:41.000+0200},
title = {Exploiting web search engines to search structured databases},
url = {http://dx.doi.org/10.1145/1526709.1526777},
year = 2009
}