Paper: Poly-co: a multilayer perceptron approach for coreference detection

ACL ID W11-1915
Title Poly-co: a multilayer perceptron approach for coreference detection
Venue International Conference on Computational Natural Language Learning
Session shared task
Year 2011
Authors

This paper details the coreference resolution system submitted by Stanford at the CoNLL- 2011 shared task. Our system is a collection of deterministic coreference resolution mod- els that incorporate lexical, syntactic, seman- tic, and discourse information. All these mod- els use global document-level information by sharing mention attributes, such as gender and number, across mentions in the same cluster. We participated in both the open and closed tracks and submitted results using both pre- dicted and gold mentions. Our system was ranked first in both tracks, with a score of 57.8 in the closed track and 58.3 in the open track.