Traditional web search engines find it challenging to achieve good search quality for recency-sensitive queries, as they are prone to delays in discovering, indexing and ranking new web pages. In this paper we introduce PreGen, an adaptive preview generation system, which is run as part of a web search engine to improve search result quality for recency-sensitive queries. PreGen uses a machine learning algorithm to classify and select live web feeds, and generates "previews" of new web pages based on the link descriptions available in these feeds. The search engine can then index and present relevant page previews as part of its search results before the pages are fetched from the web, thereby reducing end-to-end delays. Our experiments show that PreGen improves the search relevance of a state-of-the-art search engine for recency-sensitive queries by 3\% and reduces the average latencies of affected documents by 50\%.
%0 Conference Paper
%1 citeulike:12447662
%A Gurumurthy, Siva
%A Su, Hang
%A Kandylas, Vasileios
%A Venkataraman, Vidhyashankar
%B Proceedings of the 19th ACM international conference on Information and knowledge management
%C New York, NY, USA
%D 2010
%I ACM
%K citas, citeulike referencias, web
%P 1159--1168
%R 10.1145/1871437.1871584
%T Improving web search relevance and freshness with content previews
%U http://dx.doi.org/10.1145/1871437.1871584
%X Traditional web search engines find it challenging to achieve good search quality for recency-sensitive queries, as they are prone to delays in discovering, indexing and ranking new web pages. In this paper we introduce PreGen, an adaptive preview generation system, which is run as part of a web search engine to improve search result quality for recency-sensitive queries. PreGen uses a machine learning algorithm to classify and select live web feeds, and generates "previews" of new web pages based on the link descriptions available in these feeds. The search engine can then index and present relevant page previews as part of its search results before the pages are fetched from the web, thereby reducing end-to-end delays. Our experiments show that PreGen improves the search relevance of a state-of-the-art search engine for recency-sensitive queries by 3\% and reduces the average latencies of affected documents by 50\%.
%@ 978-1-4503-0099-5
@inproceedings{citeulike:12447662,
abstract = {{Traditional web search engines find it challenging to achieve good search quality for recency-sensitive queries, as they are prone to delays in discovering, indexing and ranking new web pages. In this paper we introduce PreGen, an adaptive preview generation system, which is run as part of a web search engine to improve search result quality for recency-sensitive queries. PreGen uses a machine learning algorithm to classify and select live web feeds, and generates "previews" of new web pages based on the link descriptions available in these feeds. The search engine can then index and present relevant page previews as part of its search results before the pages are fetched from the web, thereby reducing end-to-end delays. Our experiments show that PreGen improves the search relevance of a state-of-the-art search engine for recency-sensitive queries by 3\% and reduces the average latencies of affected documents by 50\%.}},
added-at = {2017-09-08T10:52:59.000+0200},
address = {New York, NY, USA},
author = {Gurumurthy, Siva and Su, Hang and Kandylas, Vasileios and Venkataraman, Vidhyashankar},
biburl = {https://www.bibsonomy.org/bibtex/2e434d6651edcc73cd73d017dba40566f/fernand0},
booktitle = {Proceedings of the 19th ACM international conference on Information and knowledge management},
citeulike-article-id = {12447662},
citeulike-linkout-0 = {http://portal.acm.org/citation.cfm?id=1871584},
citeulike-linkout-1 = {http://dx.doi.org/10.1145/1871437.1871584},
doi = {10.1145/1871437.1871584},
interhash = {9cfe08ae1c787238b0aace588dfc1433},
intrahash = {e434d6651edcc73cd73d017dba40566f},
isbn = {978-1-4503-0099-5},
keywords = {citas, citeulike referencias, web},
location = {Toronto, ON, Canada},
pages = {1159--1168},
posted-at = {2013-06-26 17:21:09},
priority = {2},
publisher = {ACM},
series = {CIKM '10},
timestamp = {2017-09-08T10:53:23.000+0200},
title = {{Improving web search relevance and freshness with content previews}},
url = {http://dx.doi.org/10.1145/1871437.1871584},
year = 2010
}