A model of language learning with semantics and meaning-preserving corrections

Dana Angluin (1) , Leonor Becerra-Bonache (2)

1 YALE - Department of Computer Science
2 LHC - Laboratoire Hubert Curien

We present a computational model that takes into account semantics for language learning and allows us to model meaning-preserving corrections. The model is constructed with a learner and a teacher who interact in a sequence of shared situations by producing utterances intended to denote a unique object in each situation. We test our model with limited sublanguages of 10 natural languages exhibiting a variety of linguistic phenomena. The results show that learning to a high level of performance occurs after a reasonable number of interactions. Comparing the effect of a teacher who does no correction to that of a teacher who corrects whenever possible, we show that under certain conditions corrections can accelerate the rate of learning. We also define and analyze a simplified model of a probabilistic process of collecting corrections to help understand the possibilities and limitations of corrections in our setting.

Domaines: Apprentissage [cs.LG]; Intelligence artificielle [cs.AI]

Dana Angluin, Leonor Becerra-Bonache. A model of language learning with semantics and meaning-preserving corrections. Artificial Intelligence, 2017, 242, pp.23-51. ⟨hal-01386949⟩