Weakly supervised parsing with rules - Archive ouverte HAL Accéder directement au contenu
Communication Dans Un Congrès Année : 2013

Weakly supervised parsing with rules

Résumé

This work proposes a new research direction to address the lack of structures in traditional n-gram models. It is based on a weakly supervised dependency parser that can model speech syntax without relying on any annotated training corpus. La- beled data is replaced by a few hand-crafted rules that encode basic syntactic knowledge. Bayesian inference then samples the rules, disambiguating and combining them to create complex tree structures that maximize a discriminative model's posterior on a target unlabeled corpus. This posterior encodes sparse se- lectional preferences between a head word and its dependents. The model is evaluated on English and Czech newspaper texts, and is then validated on French broadcast news transcriptions.
Fichier principal
Vignette du fichier
is13mypaper.pdf (219.22 Ko) Télécharger le fichier
Origine : Fichiers éditeurs autorisés sur une archive ouverte
Loading...

Dates et versions

hal-00850437 , version 1 (06-09-2013)

Identifiants

  • HAL Id : hal-00850437 , version 1

Citer

Christophe Cerisara, Alejandra Lorenzo, Pavel Kral. Weakly supervised parsing with rules. INTERSPEECH 2013, Aug 2013, Lyon, France. pp.2192-2196. ⟨hal-00850437⟩
191 Consultations
139 Téléchargements

Partager

Gmail Facebook X LinkedIn More