In the ocean of Web data, Web search engines are the primary way to access content. As the data is on the order of petabytes, current search engines are very large centralized systems based on replicated clusters. Web data, however, is always evolving. The number of Web sites continues to grow rapidly and there are currently more than 20 billion indexed pages. In the near future, centralized systems are likely to become ineffective against such a load, thus suggesting the need of fully distributed search engines. Such engines need to achieve the following goals: high quality answers, fast response time, high query throughput, and scalability. In this paper we survey and organize recent research results, outlining the main challenges of designing a distributed Web retrieval system.
%0 Conference Paper
%1 baezayates07challenges
%A Baeza-Yates, Ricardo
%A Castillo, Carlos
%A Junqueira, Flavio
%A Plachouras, Vassilis
%A Silvestri, Fabrizio
%B Proceedings of the 23rd International Conference on Data Engineering, ICDE 2007, April 15-20, 2007, The Marmara Hotel, Istanbul, Turkey
%D 2007
%K ir
%T Challenges on distributed web retrieval
%U http://www.dcc.uchile.cl/~ccastill/papers/baeza\_2007\_challenges\_distributed\_information\_retrieval.pdf
%X In the ocean of Web data, Web search engines are the primary way to access content. As the data is on the order of petabytes, current search engines are very large centralized systems based on replicated clusters. Web data, however, is always evolving. The number of Web sites continues to grow rapidly and there are currently more than 20 billion indexed pages. In the near future, centralized systems are likely to become ineffective against such a load, thus suggesting the need of fully distributed search engines. Such engines need to achieve the following goals: high quality answers, fast response time, high query throughput, and scalability. In this paper we survey and organize recent research results, outlining the main challenges of designing a distributed Web retrieval system.
@inproceedings{baezayates07challenges,
abstract = {In the ocean of Web data, Web search engines are the primary way to access content. As the data is on the order of petabytes, current search engines are very large centralized systems based on replicated clusters. Web data, however, is always evolving. The number of Web sites continues to grow rapidly and there are currently more than 20 billion indexed pages. In the near future, centralized systems are likely to become ineffective against such a load, thus suggesting the need of fully distributed search engines. Such engines need to achieve the following goals: high quality answers, fast response time, high query throughput, and scalability. In this paper we survey and organize recent research results, outlining the main challenges of designing a distributed Web retrieval system.},
added-at = {2008-07-14T14:15:30.000+0200},
author = {Baeza-Yates, Ricardo and Castillo, Carlos and Junqueira, Flavio and Plachouras, Vassilis and Silvestri, Fabrizio},
biburl = {https://www.bibsonomy.org/bibtex/2c577a49f53682f1547ee93744936a116/hpclabisti},
booktitle = {Proceedings of the 23rd International Conference on Data Engineering, ICDE 2007, April 15-20, 2007, The Marmara Hotel, Istanbul, Turkey},
citeulike-article-id = {1062382},
interhash = {4f7ee88b05ff4af7cd66bd5eb089b830},
intrahash = {c577a49f53682f1547ee93744936a116},
keywords = {ir},
posted-at = {2007-01-23 16:43:56},
priority = {4},
timestamp = {2008-07-14T16:38:03.000+0200},
title = {Challenges on distributed web retrieval},
url = {http://www.dcc.uchile.cl/~ccastill/papers/baeza\_2007\_challenges\_distributed\_information\_retrieval.pdf},
year = 2007
}