A study on automatically extracted keywords in text categorization Export

@inproceedings{citeulike:1533368, abstract = {This paper presents a study on if and how automatically extracted keywords can be used to improve text categorization. In summary we show that a higher performance --- as measured by micro-averaged F-measure on a standard text categorization collection --- is achieved when the full-text representation is combined with the automatically extracted keywords. The combination is obtained by giving higher weights to words in the full-texts that are also extracted as keywords. We also present results for experiments in which the keywords are the only input to the categorizer, either represented as unigrams or intact. Of these two experiments, the unigrams have the best performance, although neither performs as well as headlines only}, address = {Morristown, NJ, USA}, author = {Hulth, Anette and Megyesi, Be\'{a}ta B.}, booktitle = {ACL '06: Proceedings of the 21st International Conference on Computational Linguistics and the 44th annual meeting of the ACL}, citeulike-article-id = {1533368}, citeulike-linkout-0 = {http://portal.acm.org/citation.cfm?id=1220175.1220243}, citeulike-linkout-1 = {http://dx.doi.org/10.3115/1220175.1220243}, doi = {10.3115/1220175.1220243}, keywords = {categorization--automatic, classification--text--automated, keyphrase\_extraction}, pages = {537--544}, posted-at = {2007-08-03 14:31:22}, priority = {3}, publisher = {Association for Computational Linguistics}, title = {A study on automatically extracted keywords in text categorization}, url = {http://dx.doi.org/10.3115/1220175.1220243}, year = {2006} }

TY - CONF ID - citeulike:1533368 L3 - citeulike-article-id:1533368 N2 - This paper presents a study on if and how automatically extracted keywords can be used to improve text categorization. In summary we show that a higher performance --- as measured by micro-averaged F-measure on a standard text categorization collection --- is achieved when the full-text representation is combined with the automatically extracted keywords. The combination is obtained by giving higher weights to words in the full-texts that are also extracted as keywords. We also present results for experiments in which the keywords are the only input to the categorizer, either represented as unigrams or intact. Of these two experiments, the unigrams have the best performance, although neither performs as well as headlines only AD - Morristown, NJ, USA EP - 544 TI - A study on automatically extracted keywords in text categorization PB - Association for Computational Linguistics T2 - ACL '06: Proceedings of the 21st International Conference on Computational Linguistics and the 44th annual meeting of the ACL SP - 537 KW - categorization--automatic KW - classification--text--automated KW - keyphrase_extraction AU - Hulth, Anette AU - Megyesi, Beáta PY - 2006/// UR - http://dx.doi.org/10.3115/1220175.1220243 ER -