Latent structure perceptron with feature induction for unrestricted coreference resolution
Research output: Contributions to collected editions/works › Article in conference proceedings › Research › peer-review
Standard
Joint Conference on Empirical Methods in Natural Language Processing and Computational Natural Language Learning: EMNLP-CoNLL 2012; Proceedings of the Shared Task: Modeling Multilingual Unrestricted Coreference in OntoNotes, July 13, 2012. Stroudsburg: Association for Computational Linguistics (ACL), 2012. p. 41-48.
Research output: Contributions to collected editions/works › Article in conference proceedings › Research › peer-review
Harvard
APA
Vancouver
Bibtex
}
RIS
TY - CHAP
T1 - Latent structure perceptron with feature induction for unrestricted coreference resolution
AU - Fernandes, Eraldo Rezende
AU - dos Santos, Cícero Nogueira
AU - Milidiú, Ruy Luiz
PY - 2012
Y1 - 2012
N2 - We describe a machine learning system based on large margin structure perceptron for unrestricted coreference resolution that introduces two key modeling techniques: latent coreference trees and entropy guided feature induction. The proposed latent tree modeling turns the learning problem computationally feasible. Additionally, using an automatic feature induction method, we are able to efficiently build nonlinear models and, hence, achieve high performances with a linear learning algorithm. Our system is evaluated on the CoNLL-2012 Shared Task closed track, which comprises three languages: Arabic, Chinese and English. We apply the same system to all languages, except for minor adaptations on some language dependent features, like static lists of pronouns. Our system achieves an official score of 58.69, the best one among all the competitors.
AB - We describe a machine learning system based on large margin structure perceptron for unrestricted coreference resolution that introduces two key modeling techniques: latent coreference trees and entropy guided feature induction. The proposed latent tree modeling turns the learning problem computationally feasible. Additionally, using an automatic feature induction method, we are able to efficiently build nonlinear models and, hence, achieve high performances with a linear learning algorithm. Our system is evaluated on the CoNLL-2012 Shared Task closed track, which comprises three languages: Arabic, Chinese and English. We apply the same system to all languages, except for minor adaptations on some language dependent features, like static lists of pronouns. Our system achieves an official score of 58.69, the best one among all the competitors.
KW - Informatics
KW - Business informatics
UR - http://www.scopus.com/inward/record.url?scp=84918552373&partnerID=8YFLogxK
UR - https://dl.acm.org/action/showFmPdf?doi=10.5555%2F2391181
M3 - Article in conference proceedings
AN - SCOPUS:84918552373
SP - 41
EP - 48
BT - Joint Conference on Empirical Methods in Natural Language Processing and Computational Natural Language Learning
PB - Association for Computational Linguistics (ACL)
CY - Stroudsburg
T2 - 2012 Joint Conference on Empirical Methods in Natural Language Processing and Computational Natural Language Learning - EMNLP-CoNLL 2012
Y2 - 12 July 2012 through 14 July 2012
ER -