Abstract
SenseClusters is a freely available word sense discrimination system that takes a purely unsupervised clustering approach. It uses no knowledge other than what is available in a raw unstructured corpus, and clusters instances of a given target word based only on their mutual contextual similarities. It is a complete system that provides support for feature selection from large corpora, several different context representation schemes, various clustering algorithms, and evaluation of the discovered clusters.
Original language | English (US) |
---|---|
Pages | 26-29 |
Number of pages | 4 |
State | Published - 2004 |
Event | 2004 Human Language Technology Conference of the North American Chapter of the Association for Computational Linguistics - Demonstrations, HLT-NAACL 2004 - Boston, United States Duration: May 2 2004 → May 7 2004 |
Conference
Conference | 2004 Human Language Technology Conference of the North American Chapter of the Association for Computational Linguistics - Demonstrations, HLT-NAACL 2004 |
---|---|
Country/Territory | United States |
City | Boston |
Period | 5/2/04 → 5/7/04 |
Bibliographical note
Funding Information:This work has been partially supported by a National Science Foundation Faculty Early CAREER Development award (Grant #0092784).
Publisher Copyright:
© HLT-NAACL 2004 - Human Language Technology Conference of the North American Chapter of the Association for Computational Linguistics, Demonstrations. All rights reserved.