Paper: Dynamic Parameters for Cross Document Coreference

ACL ID C10-2114
Title Dynamic Parameters for Cross Document Coreference
Venue International Conference on Computational Linguistics
Session Poster Session
Year 2010

In this paper we present a new algorithm for the Person Cross Document Coreference task. We show that accurate results require a way to adapt the parameters of the similarity function – metrics and threshold – to the ontological constraints obeyed by individuals. The tech- nique we propose dynamically changes the ini- tial weights computed when the context is ana- lyzed. The weight recomputation is necessary in order to resolve clusters borders, which are inevitably blurred by a static approach. The re- sults show a significant gain in accuracy.