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 language||English (US)|
|Number of pages||4|
|State||Published - 2007|
|Event||4th International Workshop on Semantic Evaluations, SemEval 2007 - Prague, Czech Republic|
Duration: Jun 23 2007 → Jun 24 2007
|Other||4th International Workshop on Semantic Evaluations, SemEval 2007|
|Period||6/23/07 → 6/24/07|
Bibliographical noteFunding Information:
This research was partially supported by the National Science Foundation Faculty Early Career Development (CAREER) Program (#0092784).
© 2007 Association for Computational Linguistics.