An evaluation of evolved term-weighting schemes in
information retrieval
R. Cummins, and C. O'Riordan. CIKM '05: Proceedings of the 14th ACM international
conference on Information and knowledge management, page 305--306. Bremen, Germany, ACM press, (31 October - 5 November 2005)
Abstract
presents an evaluation of evolved term-weighting
schemes on short, medium and long TREC queries. A
previously evolved global (collection-wide)
term-weighting scheme is evaluated on unseen TREC data
and is shown to increase mean average precision over
idf. A local (within-document) evolved term-weighting
scheme is presented which is dependent on the best
performing global scheme. The full evolved scheme (i.e.
the combined local and global scheme) is compared to
both the BM25 scheme and the Pivoted Normalisation
scheme. Our results show that the local evolved
solution does not perform well on some collections due
to its document normalisation properties and we
conclude that Okapi-tf can be tuned to interact
effectively with the evolved global weighting scheme
presented and increase mean average precision over the
standard BM25 scheme.
%0 Conference Paper
%1 cummins:2005:CIKM
%A Cummins, Ronan
%A O'Riordan, Colm
%B CIKM '05: Proceedings of the 14th ACM international
conference on Information and knowledge management
%C Bremen, Germany
%D 2005
%E Herzog, Otthein
%E Schek, Hans-Jorg
%E Fuhr, Norbert
%E Chowdhury, Abdur
%E Teiken, Wilfried
%I ACM press
%K Poster Session algorithms, genetic information programming, retrieval, term-weighting,
%P 305--306
%T An evaluation of evolved term-weighting schemes in
information retrieval
%U http://portal.acm.org/citation.cfm?doid=1099639
%X presents an evaluation of evolved term-weighting
schemes on short, medium and long TREC queries. A
previously evolved global (collection-wide)
term-weighting scheme is evaluated on unseen TREC data
and is shown to increase mean average precision over
idf. A local (within-document) evolved term-weighting
scheme is presented which is dependent on the best
performing global scheme. The full evolved scheme (i.e.
the combined local and global scheme) is compared to
both the BM25 scheme and the Pivoted Normalisation
scheme. Our results show that the local evolved
solution does not perform well on some collections due
to its document normalisation properties and we
conclude that Okapi-tf can be tuned to interact
effectively with the evolved global weighting scheme
presented and increase mean average precision over the
standard BM25 scheme.
%@ 1-59593-140-6
@inproceedings{cummins:2005:CIKM,
abstract = {presents an evaluation of evolved term-weighting
schemes on short, medium and long TREC queries. A
previously evolved global (collection-wide)
term-weighting scheme is evaluated on unseen TREC data
and is shown to increase mean average precision over
idf. A local (within-document) evolved term-weighting
scheme is presented which is dependent on the best
performing global scheme. The full evolved scheme (i.e.
the combined local and global scheme) is compared to
both the BM25 scheme and the Pivoted Normalisation
scheme. Our results show that the local evolved
solution does not perform well on some collections due
to its document normalisation properties and we
conclude that Okapi-tf can be tuned to interact
effectively with the evolved global weighting scheme
presented and increase mean average precision over the
standard BM25 scheme.},
added-at = {2008-06-19T17:35:00.000+0200},
address = {Bremen, Germany},
author = {Cummins, Ronan and O'Riordan, Colm},
biburl = {https://www.bibsonomy.org/bibtex/24d265e86c0f3c6479df83c7ab99c4ac8/brazovayeye},
booktitle = {CIKM '05: Proceedings of the 14th ACM international
conference on Information and knowledge management},
editor = {Herzog, Otthein and Schek, Hans-Jorg and Fuhr, Norbert and Chowdhury, Abdur and Teiken, Wilfried},
interhash = {2a11faf8ad214f3e78b14dd82a90bb4d},
intrahash = {4d265e86c0f3c6479df83c7ab99c4ac8},
isbn = {1-59593-140-6},
keywords = {Poster Session algorithms, genetic information programming, retrieval, term-weighting,},
month = {31 October - 5 November},
notes = {Proceedings of the 14th ACM international conference
on Information and knowledge management},
order_no = {605050},
organisation = {ACM},
pages = {305--306},
publisher = {ACM press},
publisher_address = {New York, NY, USA},
size = {2 pages},
timestamp = {2008-06-19T17:38:15.000+0200},
title = {An evaluation of evolved term-weighting schemes in
information retrieval},
url = {http://portal.acm.org/citation.cfm?doid=1099639},
year = 2005
}