Paper: Instance Sense Induction from Attribute Sets

ACL ID C10-2094
Title Instance Sense Induction from Attribute Sets
Venue International Conference on Computational Linguistics
Session Poster Session
Year 2010
Authors

This paper investigates the new problem of automatic sense induction for instance names using automatically extracted at- tribute sets. Several clustering strategies and data sources are described and eval- uated. We also discuss the drawbacks of the evaluation metrics commonly used in similar clustering tasks. The results show improvements in most metrics with re- spect to the baselines, especially for pol- ysemous instances.