Efficient Pruning of Probabilistic Automata - Université Jean-Monnet-Saint-Étienne Access content directly
Conference Papers Year : 2008

Efficient Pruning of Probabilistic Automata

Franck Thollard
  • Function : Author
  • PersonId : 841732
Baptiste Jeudy

Abstract

Applications of probabilistic grammatical inference are limited due to time and space consuming constraints. In statistical language modeling, for example, large corpora are now available and lead to managing automata with millions of states. We propose in this article a method for pruning automata (when restricted to tree based structures) which is not only efficient (sub-quadratic) but that allows to dramatically reduce the size of the automaton with a small impact on the underlying distribution. Results are evaluated on a language modeling task.
Fichier principal
Vignette du fichier
sspr08_pruning.pdf (393.19 Ko) Télécharger le fichier
Origin : Files produced by the author(s)

Dates and versions

ujm-00322818 , version 1 (09-03-2009)

Identifiers

  • HAL Id : ujm-00322818 , version 1

Cite

Franck Thollard, Baptiste Jeudy. Efficient Pruning of Probabilistic Automata. Structural and Statistical Pattern Recognition, Dec 2008, Orlando, United States. pp.65-75. ⟨ujm-00322818⟩
71 View
98 Download

Share

Gmail Facebook X LinkedIn More