UMND2: SenseClusters applied to the sense induction task of SENSEVAL-4

Research output: Contribution to conferencePaperpeer-review

11 Scopus citations

Abstract

SenseClusters is a freely-available open- source system that served as the University of Minnesota, Duluth entry in the SENSEVAL-4 sense induction task. For this task SenseClusters was configured to construct representations of the instances to be clustered using the centroid of word cooccurrence vectors that replace the words in an instance. These instances are then clustered using k-means where the number of clusters is discovered automatically using the Adapted Gap Statistic. In these experiments SenseClusters did not use any information outside of the raw untagged text that was to be clustered, and no tuning of the system was performed using external corpora.

Original languageEnglish (US)
Pages394-397
Number of pages4
StatePublished - Jan 1 2007
Externally publishedYes
Event4th International Workshop on Semantic Evaluations, SemEval 2007 - Prague, Czech Republic
Duration: Jun 23 2007Jun 24 2007

Other

Other4th International Workshop on Semantic Evaluations, SemEval 2007
CountryCzech Republic
CityPrague
Period6/23/076/24/07

Fingerprint Dive into the research topics of 'UMND2: SenseClusters applied to the sense induction task of SENSEVAL-4'. Together they form a unique fingerprint.

Cite this