%0 Conference Paper %1 pairedFscore %A Artiles, Javier %A Amigó, Enrique %A Gonzalo, Julio %B Proceedings of the 2009 Conference on Empirical Methods in Natural Language Processing: Volume 2 - Volume 2 %C Stroudsburg, PA, USA %D 2009 %I Association for Computational Linguistics %K cluster clustering evaluation f-score fscore measure paired %P 534--542 %T The role of named entities in web people search %U http://dl.acm.org/citation.cfm?id=1699571.1699582 %X The ambiguity of person names in the Web has become a new area of interest for NLP researchers. This challenging problem has been formulated as the task of clustering Web search results (returned in response to a person name query) according to the individual they mention. In this paper we compare the coverage, reliability and independence of a number of features that are potential information sources for this clustering task, paying special attention to the role of named entities in the texts to be clustered. Although named entities are used in most approaches, our results show that, independently of the Machine Learning or Clustering algorithm used, named entity recognition and classification per se only make a small contribution to solve the problem. %@ 978-1-932432-62-6

@inproceedings{pairedFscore, abstract = {The ambiguity of person names in the Web has become a new area of interest for NLP researchers. This challenging problem has been formulated as the task of clustering Web search results (returned in response to a person name query) according to the individual they mention. In this paper we compare the coverage, reliability and independence of a number of features that are potential information sources for this clustering task, paying special attention to the role of named entities in the texts to be clustered. Although named entities are used in most approaches, our results show that, independently of the Machine Learning or Clustering algorithm used, named entity recognition and classification per se only make a small contribution to solve the problem.}, acmid = {1699582}, added-at = {2011-09-18T22:32:05.000+0200}, address = {Stroudsburg, PA, USA}, author = {Artiles, Javier and Amig\'{o}, Enrique and Gonzalo, Julio}, biburl = {https://www.bibsonomy.org/bibtex/20508fd651c5b88332d5997c2392fe06d/jil}, booktitle = {Proceedings of the 2009 Conference on Empirical Methods in Natural Language Processing: Volume 2 - Volume 2}, interhash = {1df028d9ddac8b245a5a34aa183dc159}, intrahash = {0508fd651c5b88332d5997c2392fe06d}, isbn = {978-1-932432-62-6}, keywords = {cluster clustering evaluation f-score fscore measure paired}, location = {Singapore}, numpages = {9}, pages = {534--542}, publisher = {Association for Computational Linguistics}, series = {EMNLP '09}, timestamp = {2013-11-23T20:11:51.000+0100}, title = {The role of named entities in web people search}, url = {http://dl.acm.org/citation.cfm?id=1699571.1699582}, year = 2009 }