Effects of meaning-preserving corrections on language learning

Authors:
Dana Angluin;Leonor Becerra-Bonache
Affiliations:
Yale University;Université de Saint-Etienne, France
Venue:
CoNLL '11 Proceedings of the Fifteenth Conference on Computational Natural Language Learning
Year:
2011

Citing 1
Cited 1

C++

Computer Standards & Interfaces - Special double issue: the programming language standards scene, ten years on

An Overview of How Semantics and Corrections Can Help Language Learning

WI-IAT '11 Proceedings of the 2011 IEEE/WIC/ACM International Conferences on Web Intelligence and Intelligent Agent Technology - Volume 03

Quantified Score

Hi-index	0.02

Visualization

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.