Speeding Up Syntactic Learning Using Contextual Information

Abstract : It has been shown in (Angluin and Becerra-Bonache, 2010, 2011) that interactions between a learner and a teacher can help language learning. In this paper, we make use of additional contextual information in a pairwise-based generative approach aiming at learning (situation,sentence)-pair-hidden markov models. We show that this allows a significant speed-up of the convergence of the syntactic learning. We apply our model on a toy natural language task in Spanish dealing with geometric objects.
Document type :
Conference papers
Complete list of metadatas

Cited literature [5 references]  Display  Hide  Download

https://hal.archives-ouvertes.fr/hal-00717809
Contributor : Leonor Becerra-Bonache <>
Submitted on : Friday, July 13, 2012 - 4:36:34 PM
Last modification on : Wednesday, July 25, 2018 - 2:05:30 PM
Long-term archiving on : Sunday, October 14, 2012 - 3:20:22 AM

File

becerra2012.pdf
Files produced by the author(s)

Identifiers

  • HAL Id : hal-00717809, version 1

Collections

Citation

Leonor Becerra-Bonache, Elisa Fromont, Amaury Habrard, Michael Perrot, Marc Sebban. Speeding Up Syntactic Learning Using Contextual Information. International Conference on Grammatical Inference, Sep 2012, United States. pp.49-53. ⟨hal-00717809⟩

Share

Metrics

Record views

285

Files downloads

161