Weakly supervised parsing with rules - Archive ouverte HAL Access content directly
Conference Papers Year : 2013

Weakly supervised parsing with rules

(1) , (1) , (2)
1
2

Abstract

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
Origin : Publisher files allowed on an open archive
Loading...

Dates and versions

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

Identifiers

  • HAL Id : hal-00850437 , version 1

Cite

Christophe Cerisara, Alejandra Lorenzo, Pavel Kral. Weakly supervised parsing with rules. INTERSPEECH 2013, Aug 2013, Lyon, France. pp.2192-2196. ⟨hal-00850437⟩
189 View
117 Download

Share

Gmail Facebook Twitter LinkedIn More