Speeding Up Syntactic Learning Using Contextual Information

Leonor Becerra Bonache, Elisa Fromont, Amaury Habrard, Michaël Perrot, Marc Sebban
Proceedings of the Eleventh International Conference on Grammatical Inference, PMLR 21:49-53, 2012.

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.

Cite this Paper

BibTeX
@InProceedings{pmlr-v21-becerra12a, title = {Speeding Up Syntactic Learning Using Contextual Information}, author = {Bonache, Leonor Becerra and Fromont, Elisa and Habrard, Amaury and Perrot, Michaël and Sebban, Marc}, booktitle = {Proceedings of the Eleventh International Conference on Grammatical Inference}, pages = {49--53}, year = {2012}, editor = {Heinz, Jeffrey and Higuera, Colin and Oates, Tim}, volume = {21}, series = {Proceedings of Machine Learning Research}, address = {University of Maryland, College Park, MD, USA}, month = {05--08 Sep}, publisher = {PMLR}, pdf = {http://proceedings.mlr.press/v21/becerra12a/becerra12a.pdf}, url = {https://proceedings.mlr.press/v21/becerra12a.html}, 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.} }
Endnote
%0 Conference Paper %T Speeding Up Syntactic Learning Using Contextual Information %A Leonor Becerra Bonache %A Elisa Fromont %A Amaury Habrard %A Michaël Perrot %A Marc Sebban %B Proceedings of the Eleventh International Conference on Grammatical Inference %C Proceedings of Machine Learning Research %D 2012 %E Jeffrey Heinz %E Colin Higuera %E Tim Oates %F pmlr-v21-becerra12a %I PMLR %P 49--53 %U https://proceedings.mlr.press/v21/becerra12a.html %V 21 %X 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.
RIS
TY - CPAPER TI - Speeding Up Syntactic Learning Using Contextual Information AU - Leonor Becerra Bonache AU - Elisa Fromont AU - Amaury Habrard AU - Michaël Perrot AU - Marc Sebban BT - Proceedings of the Eleventh International Conference on Grammatical Inference DA - 2012/08/16 ED - Jeffrey Heinz ED - Colin Higuera ED - Tim Oates ID - pmlr-v21-becerra12a PB - PMLR DP - Proceedings of Machine Learning Research VL - 21 SP - 49 EP - 53 L1 - http://proceedings.mlr.press/v21/becerra12a/becerra12a.pdf UR - https://proceedings.mlr.press/v21/becerra12a.html AB - 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. ER -
APA
Bonache, L.B., Fromont, E., Habrard, A., Perrot, M. & Sebban, M.. (2012). Speeding Up Syntactic Learning Using Contextual Information. Proceedings of the Eleventh International Conference on Grammatical Inference, in Proceedings of Machine Learning Research 21:49-53 Available from https://proceedings.mlr.press/v21/becerra12a.html.

Related Material