Learning Simple External Contextual Languages from Positive Data

Leonor Becerra-Bonache (1)

1 LHC - Laboratoire Hubert Curien

The field of Grammatical Inference provides a good theoretical framework for investigating a learning process. Formal results in this field can be relevant to the question of first language acquisition. However, Grammatical Inference studies have been focused mainly on mathematical aspects, and have not exploited the linguistic relevance of their results. With this paper, we try to enrich Grammatical Inference studies with ideas from Linguistics. We propose a non-classical mechanism that has relevant linguistic and computational properties, and we study its learnability from positive data.

Domaines: Apprentissage [cs.LG]

Leonor Becerra-Bonache. Learning Simple External Contextual Languages from Positive Data. Triangle, 2012, pp.1-18. ⟨hal-00755304⟩