Carregant...
Carregant...

Vés al contingut (premeu Retorn)

Unsupervised spectral learning of WCFG as low-rank matrix completion

Autor
Bailly, R.; Carreras, X.; Luque, F. M.; Quattoni, A.J.
Tipus d'activitat
Presentació treball a congrés
Nom de l'edició
2013 Conference on Empirical Methods in Natural Language Processing
Any de l'edició
2013
Data de presentació
2013-10-19
Llibre d'actes
Proceedings of the 2013 Conference on Empirical Methods in Natural Language Processing
Pàgina inicial
624
Pàgina final
635
Editor
Association for Computational Linguistics
Projecte finançador
Biological and Social Data Mining: Algorithms, Theory, and Implementations (TIN2011-27479-C04-03)
Cross-lingual Knowledge Extraction
TACARDI: Traducción Automática en Contexto y Aumentada con Recursos Dinámicos de Internet
VISEN ,CHIST-ERA CALL 2011
Repositori
http://hdl.handle.net/2117/21076 Obrir en finestra nova
Resum
We derive a spectral method for unsupervised learning of Weighted Context Free Grammars. We frame WCFG induction as finding a Hankel matrix that has low rank and is linearly constrained to represent a function computed by inside-outside recursions. The proposed algorithm picks the grammar that agrees with a sample and is the simplest with respect to the nuclear norm of the Hankel matrix. We derive a spectral method for unsupervised learning ofWeighted Context Free Grammars. We frame WCFG inducti...
Citació
Bailly, R. [et al.]. Unsupervised spectral learning of WCFG as low-rank matrix completion. A: Conference on Empirical Methods in Natural Language Processing. "Proceedings of the 2013 Conference on Empirical Methods in Natural Language Processing". Seattle: Association for Computational Linguistics, 2013, p. 624-635.
Grup de recerca
GPLN - Grup de Processament del Llenguatge Natural
LARCA - Laboratori d'Algorísmia Relacional, Complexitat i Aprenentatge

Participants

  • Bailly, Raphaël  (autor ponent)
  • Carreras Perez, Xavier  (autor ponent)
  • Luque, Franco M.  (autor ponent)
  • Quattoni, Ariadna Julieta  (autor ponent)

Arxius