PASCAL - Pattern Analysis, Statistical Modelling and Computational Learning

Effects of Meaning-Preserving Corrections on Language Learning
Dana Angluin and Leonor Becerra
In: CoNLL 2011, 23-24 June 2011, Portland, Oregon, USA.

Abstract

We present a computational model of language learning via a sequence of interactions between a teacher and a learner. Experiments learning limited sublanguages of 10 natural languages show that the learner achieves a high level of performance after a reasonable number of interactions, the teacher can produce meaning-preserving corrections of the learner's utterances, and the learner can detect them. The learner does not treat corrections specially; nonetheless in several cases, significantly fewer interactions are needed by a learner interacting with a correcting teacher than with a non-correcting teacher.

EPrint Type:Conference or Workshop Item (Paper)
Project Keyword:Project Keyword UNSPECIFIED
Subjects:Computational, Information-Theoretic Learning with Statistics
ID Code:8541
Deposited By:Leonor Becerra
Deposited On:21 February 2012