@gromgull

Discovering word senses from text

, and . Proceedings of the eighth ACM SIGKDD international conference on Knowledge discovery and data mining, page 613-619. (2002)
DOI: http://doi.acm.org/10.1145/775047.775138

Description

The clustering is interesting. Once an element E is assigned to a cluster C, the overlapping features from C are subtracted from E, and E is kept in the list of elements to cluster. This lets you find different word-senses (here, in general multi-cluster membership)

Links and resources

Tags

community