%0 Conference Paper %1 citeulike:691975 %A Cohen, W. %A Richman, J. %B ACM SIGIR'01 workshop on Mathematical /Formal Methods in IR, 2001. %D 2001 %K named-entity news %T Learning to match and cluster entity names %U http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.21.3842 %X Introduction Information retrieval is, in large part, the study of methods for assessing the similarity of pairs of documents. Document similarity metrics have been used for many tasks including ad hoc document retrieval, text classification YC1994, and summarization GC1998,SSMB1997. Another problem area in which similarity metrics are central is record linkage (e.g., KA1985), where one wishes to determine if two database records taken from different source databases refer to the same...

@inproceedings{citeulike:691975, abstract = {Introduction Information retrieval is, in large part, the study of methods for assessing the similarity of pairs of documents. Document similarity metrics have been used for many tasks including ad hoc document retrieval, text classification [YC1994], and summarization [GC1998,SSMB1997]. Another problem area in which similarity metrics are central is record linkage (e.g., [KA1985]), where one wishes to determine if two database records taken from different source databases refer to the same...}, added-at = {2009-07-01T11:12:30.000+0200}, author = {Cohen, W. and Richman, J.}, biburl = {https://www.bibsonomy.org/bibtex/2c2a00307695e437f95d73e33cb0cf968/brusilovsky}, booktitle = {ACM SIGIR'01 workshop on Mathematical /Formal Methods in IR, 2001.}, citeulike-article-id = {691975}, interhash = {3b1c3fa235f785944a2bf70b34a7da3d}, intrahash = {c2a00307695e437f95d73e33cb0cf968}, keywords = {named-entity news}, posted-at = {2006-06-10 22:20:09}, priority = {2}, timestamp = {2009-07-01T11:12:40.000+0200}, title = {Learning to match and cluster entity names}, url = {http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.21.3842}, year = 2001 }