Paper: Exploring Lexicalized Features for Coreference Resolution

ACL ID W11-1905
Title Exploring Lexicalized Features for Coreference Resolution
Venue International Conference on Computational Natural Language Learning
Session shared task
Year 2011
Authors

We introduce an incremental model for coref- erence resolution that competed in the CoNLL 2011 shared task (open regular). We decided to participate with our baseline model, since it worked well with two other datasets. The ben- efits of an incremental over a mention-pair ar- chitecture are: a drastic reduction of the num- ber of candidate pairs, a means to overcome the problem of underspecified items in pair- wise classification and the natural integration of global constraints such as transitivity. We do not apply machine learning, instead the system uses an empirically derived salience measure based on the dependency labels of the true mentions. Our experiments seem to indi- cate that such a system already is on par with machine learning approaches.