Authors
Eric Charton, Michel Gagnon
Publication date
2011/6
Conference
Proceedings of the Fifteenth Conference on Computational Natural Language Learning: Shared Task
Pages
97-101
Description
This paper presents the coreference resolution system Poly-co submitted to the closed track of the CoNLL-2011 Shared Task. Our system integrates a multilayer perceptron classifier in a pipeline approach. We describe the heuristic used to select the pairs of coreference candidates that are feeded to the network for training, and our feature selection method. The features used in our approach are based on similarity and identity measures, filtering informations, like gender and number, and other syntactic information.
Scholar articles
E Charton, M Gagnon - Proceedings of the Fifteenth Conference on …, 2011