Improving pairwise coreference models through feature space hierarchy learning

Emmanuel Lassalle 1 Pascal Denis 2
1 ALPAGE - Analyse Linguistique Profonde à Grande Echelle ; Large-scale deep linguistic processing
Inria Paris-Rocquencourt, UPD7 - Université Paris Diderot - Paris 7
2 MAGNET - Machine Learning in Information Networks
LIFL - Laboratoire d'Informatique Fondamentale de Lille, Inria Lille - Nord Europe
Abstract : This paper proposes a new method for significantly improving the performance of pairwise coreference models. Given a set of indicators, our method learns how to best separate types of mention pairs into equivalence classes for which we construct distinct classification models. In effect, our approach finds an optimal feature space (derived from a base feature set and indicator set) for discriminating coreferential mention pairs. Although our approach explores a very large space of possible feature spaces, it remains tractable by exploiting the structure of the hierarchies built from the indicators. Our experiments on the CoNLL-2012 Shared Task English datasets (gold mentions) indicate that our method is robust relative to different clustering strategies and evaluation metrics, showing large and consistent improvements over a single pairwise model using the same base features. Our best system obtains a competitive 67:2 of average F1 over MUC, B3 , and CEAF which, despite its simplicity, places it above the mean score of other systems on these datasets.
Type de document :
Communication dans un congrès
ACL 2013 - Annual meeting of the Association for Computational Linguistics, Aug 2013, Sofia, Bulgaria. 2013
Liste complète des métadonnées

Littérature citée [26 références]  Voir  Masquer  Télécharger

https://hal.inria.fr/hal-00838192
Contributeur : Pascal Denis <>
Soumis le : mardi 25 juin 2013 - 08:41:10
Dernière modification le : jeudi 15 novembre 2018 - 20:27:26
Document(s) archivé(s) le : jeudi 26 septembre 2013 - 04:18:38

Fichier

main.pdf
Fichiers produits par l'(les) auteur(s)

Identifiants

  • HAL Id : hal-00838192, version 1

Citation

Emmanuel Lassalle, Pascal Denis. Improving pairwise coreference models through feature space hierarchy learning. ACL 2013 - Annual meeting of the Association for Computational Linguistics, Aug 2013, Sofia, Bulgaria. 2013. 〈hal-00838192〉

Partager

Métriques

Consultations de la notice

564

Téléchargements de fichiers

163