%0 Conference Paper %1 Lin98termClustering %A Lin, Dekang %B Proceedings of the 17th international conference on Computational linguistics %C Morristown, NJ, USA %D 1998 %I Association for Computational Linguistics %K 98 Lin clustering distributional semantics similarity term %P 768--774 %R http://dx.doi.org/10.3115/980691.980696 %T Automatic retrieval and clustering of similar words %U http://portal.acm.org/citation.cfm?id=980696 %X Bootstrapping semantics from text is one of the greatest challenges in natural language learning. We first define a word similarity measure based on the distributional pattern of words. The similarity measure allows us to construct a thesaurus using a parsed corpus. We then present a new evaluation methodology for the automatically constructed thesaurus. The evaluation results show that the thesaurus is significantly closer to WordNet than Roget Thesaurus is.

@inproceedings{Lin98termClustering, abstract = {Bootstrapping semantics from text is one of the greatest challenges in natural language learning. We first define a word similarity measure based on the distributional pattern of words. The similarity measure allows us to construct a thesaurus using a parsed corpus. We then present a new evaluation methodology for the automatically constructed thesaurus. The evaluation results show that the thesaurus is significantly closer to WordNet than Roget Thesaurus is.}, added-at = {2010-03-09T21:52:02.000+0100}, address = {Morristown, NJ, USA}, author = {Lin, Dekang}, biburl = {https://www.bibsonomy.org/bibtex/23b08719db9a27c9e8fa0d5d8f5c19a10/lee_peck}, booktitle = {Proceedings of the 17th international conference on Computational linguistics}, description = {Automatic retrieval and clustering of similar words}, doi = {http://dx.doi.org/10.3115/980691.980696}, interhash = {686133b216cc5960608af406a8f52287}, intrahash = {3b08719db9a27c9e8fa0d5d8f5c19a10}, keywords = {98 Lin clustering distributional semantics similarity term}, location = {Montreal, Quebec, Canada}, pages = {768--774}, publisher = {Association for Computational Linguistics}, timestamp = {2010-03-09T21:52:02.000+0100}, title = {Automatic retrieval and clustering of similar words}, url = {http://portal.acm.org/citation.cfm?id=980696}, year = 1998 }