Poly-co: an unsupervised co-reference detection system

Authors:
Éric Charton;Michel Gagnon;Benoit Ozell
Affiliations:
École Polytechnique de Montréal, Montreal, QC, Canada;École Polytechnique de Montréal, Montreal, QC, Canada;École Polytechnique de Montréal, Montreal, QC, Canada
Venue:
INLG '10 Proceedings of the 6th International Natural Language Generation Conference
Year:
2010

Citing 1
Cited 1

Speech and Language Processing: An Introduction to Natural Language Processing, Computational Linguistics, and Speech Recognition

Speech and Language Processing: An Introduction to Natural Language Processing, Computational Linguistics, and Speech Recognition

Poly-co: a multilayer perceptron approach for coreference detection

CONLL Shared Task '11 Proceedings of the Fifteenth Conference on Computational Natural Language Learning: Shared Task

Quantified Score

Hi-index	0.00

Visualization

Abstract

We describe our contribution to the Generation Challenge 2010 for the tasks of Named Entity Recognition and co-reference detection (GREC-NER). To extract the NE and the referring expressions, we employ a combination of a Part of Speech Tagger and the Conditional Random Fields (CRF) learning technique. We finally experiment an original algorithm to detect co-references. We conclude with discussion about our system performances.