Improving pairwise coreference models ...
Type de document :
Communication dans un congrès avec actes
Titre :
Improving pairwise coreference models through feature space hierarchy learning
Auteur(s) :
Lassalle, Emmanuel [Auteur]
Analyse Linguistique Profonde à Grande Echelle ; Large-scale deep linguistic processing [ALPAGE]
Denis, Pascal [Auteur]
Machine Learning in Information Networks [MAGNET]
Analyse Linguistique Profonde à Grande Echelle ; Large-scale deep linguistic processing [ALPAGE]
Denis, Pascal [Auteur]
Machine Learning in Information Networks [MAGNET]
Titre de la manifestation scientifique :
ACL 2013 - Annual meeting of the Association for Computational Linguistics
Organisateur(s) de la manifestation scientifique :
Association for Computational Linguistics
Ville :
Sofia
Pays :
Bulgarie
Date de début de la manifestation scientifique :
2013-08-04
Date de publication :
2013
Discipline(s) HAL :
Informatique [cs]/Informatique et langage [cs.CL]
Résumé en anglais : [en]
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 ...
Lire la suite >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.Lire moins >
Lire la suite >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.Lire moins >
Langue :
Anglais
Comité de lecture :
Oui
Audience :
Internationale
Vulgarisation :
Non
Collections :
Source :
Fichiers
- https://hal.inria.fr/hal-00838192/document
- Accès libre
- Accéder au document
- https://hal.inria.fr/hal-00838192/document
- Accès libre
- Accéder au document
- https://hal.inria.fr/hal-00838192/document
- Accès libre
- Accéder au document
- document
- Accès libre
- Accéder au document
- main.pdf
- Accès libre
- Accéder au document