Joint Anaphoricity Detection and Coreference Resolution with Constrained Latent Structures - Archive ouverte HAL Accéder directement au contenu
Communication Dans Un Congrès Année : 2015

Joint Anaphoricity Detection and Coreference Resolution with Constrained Latent Structures

Résumé

This paper introduces a new structured model for learning anaphoricity detection and coreference resolution in a joint fashion. Specifically, we use a latent tree to represent the full coreference and anaphoric structure of a document at a global level, and we jointly learn the parameters of the two models using a version of the structured perceptron algorithm. Our joint structured model is further refined by the use of pairwise constraints which help the model to capture accurately certain patterns of coreference. Our experiments on the CoNLL-2012 English datasets show large improvements in both coreference resolution and anaphoricity detection, compared to various competing architectures. Our best coreference system obtains a CoNLL score of 81:97 on gold mentions, which is to date the best score reported on this setting.
Fichier principal
Vignette du fichier
main_nocopyright.pdf (249.96 Ko) Télécharger le fichier
Origine : Fichiers produits par l'(les) auteur(s)
Loading...

Dates et versions

hal-01205189 , version 1 (28-09-2015)

Identifiants

  • HAL Id : hal-01205189 , version 1

Citer

Emmanuel Lassalle, Pascal Denis. Joint Anaphoricity Detection and Coreference Resolution with Constrained Latent Structures. AAAI Conference on Artificial Intelligence (AAAI 2015), Jan 2015, Austin, Texas, United States. ⟨hal-01205189⟩
254 Consultations
101 Téléchargements

Partager

Gmail Facebook X LinkedIn More