Automatic retrieval and clustering of similar words Export

@inproceedings{citeulike:1611899, 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.}, address = {Morristown, NJ, USA}, author = {Lin, Dekang}, booktitle = {Proceedings of the 17th international conference on Computational linguistics}, citeulike-article-id = {1611899}, citeulike-linkout-0 = {http://portal.acm.org/citation.cfm?id=980696}, citeulike-linkout-1 = {http://dx.doi.org/10.3115/980432.980696}, doi = {10.3115/980432.980696}, keywords = {semantic\_similarity, word\_clustering, word\_similarity}, location = {Montreal, Quebec, Canada}, pages = {768--774}, posted-at = {2009-10-22 16:26:48}, priority = {2}, publisher = {Association for Computational Linguistics}, title = {Automatic retrieval and clustering of similar words}, url = {http://dx.doi.org/10.3115/980432.980696}, year = {1998} }

TY - CONF ID - citeulike:1611899 L3 - citeulike-article-id:1611899 N2 - 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. CY - Montreal, Quebec, Canada AD - Morristown, NJ, USA EP - 774 TI - Automatic retrieval and clustering of similar words PB - Association for Computational Linguistics T2 - Proceedings of the 17th international conference on Computational linguistics SP - 768 KW - semantic_similarity KW - word_clustering KW - word_similarity AU - Lin, Dekang PY - 1998/// UR - http://dx.doi.org/10.3115/980432.980696 ER -