Toric grammars: a new statistical approach to natural language modeling

Olivier Catoni 1, 2 Thomas Mainguy 1, 2
2 CLASSIC - Computational Learning, Aggregation, Supervised Statistical, Inference, and Classification
DMA - Département de Mathématiques et Applications - ENS Paris, ENS Paris - École normale supérieure - Paris, Inria Paris-Rocquencourt
Abstract : We propose a new statistical model for computational linguistics. Rather than trying to estimate directly the probability distribution of a random sentence of the language, we define a Markov chain on finite sets of sentences with many finite recurrent communicating classes and define our language model as the invariant probability measures of the chain on each recurrent communicating class. This Markov chain, that we call a communication model, recombines at each step randomly the set of sentences forming its current state, using some grammar rules. When the grammar rules are fixed and known in advance instead of being estimated on the fly, we can prove supplementary mathematical properties. In particular, we can prove in this case that all states are recurrent states, so that the chain defines a partition of its state space into finite recurrent communicating classes. We show that our approach is a decisive departure from Markov models at the sentence level and discuss its relationships with Context Free Grammars. Although the toric grammars we use are closely related to Context Free Grammars, the way we generate the language from the grammar is qualitatively different. Our communication model has two purposes. On the one hand, it is used to define indirectly the probability distribution of a random sentence of the language. On the other hand it can serve as a (crude) model of language transmission from one speaker to another speaker through the communication of a (large) set of sentences.
Liste complète des métadonnées

https://hal.archives-ouvertes.fr/hal-00934487
Contributeur : Olivier Catoni <>
Soumis le : mercredi 22 janvier 2014 - 10:23:35
Dernière modification le : vendredi 25 mai 2018 - 12:02:06

Lien texte intégral

Identifiants

  • HAL Id : hal-00934487, version 1
  • ARXIV : 1302.2569

Collections

Citation

Olivier Catoni, Thomas Mainguy. Toric grammars: a new statistical approach to natural language modeling. 2013. 〈hal-00934487〉

Partager

Métriques

Consultations de la notice

231