Carregant...
Carregant...

Vés al contingut (premeu Retorn)

Spectral learning of weighted automata: a forward-backward perspective

Autor
de Balle, B.; Carreras, X.; Luque, F. M.; Quattoni, A.J.
Tipus d'activitat
Article en revista
Revista
Machine learning
Data de publicació
2013-10-07
Número
October
Pàgina inicial
1
Pàgina final
31
DOI
https://doi.org/10.1007/s10994-013-5416-x Obrir en finestra nova
Projecte finançador
Biological and Social Data Mining: Algorithms, Theory, and Implementations (TIN2011-27479-C04-03)
Cross-lingual Knowledge Extraction
Pattern Analysis, Statistical Modelling, and Computational Learning 2 (PASCAL2)
Repositori
http://hdl.handle.net/2117/21075 Obrir en finestra nova
URL
http://link.springer.com/article/10.1007%2Fs10994-013-5416-x Obrir en finestra nova
Resum
In recent years we have seen the development of efficient provably correct algorithms for learning Weighted Finite Automata (WFA). Most of these algorithms avoid the known hardness results by defining parameters beyond the number of states that can be used to quantify the complexity of learning automata under a particular distribution. One such class of methods are the so-called spectral algorithms that measure learning complexity in terms of the smallest singular value of some Hankel matrix. Ho...
Citació
Balle, B. [et al.]. Spectral learning of weighted automata: a forward-backward perspective. "Machine learning", 07 Octubre 2013, núm. October, p. 1-31.
Paraules clau
Spectral learning Weighted finite automata Dependency parsing
Grup de recerca
GPLN - Grup de Processament del Llenguatge Natural
LARCA - Laboratori d'Algorísmia Relacional, Complexitat i Aprenentatge

Participants

  • de Balle Pigem, Borja  (autor)
  • Carreras Perez, Xavier  (autor)
  • Luque, Franco M.  (autor)
  • Quattoni, Ariadna Julieta  (autor)