Computational Models of Tutor Feedback in Language Acquisition

Jens Nevens, Michael Spranger

Onderzoeksoutput: Conference paper

3 Citaten (Scopus)

Samenvatting

This paper investigates the role of tutor feedback in language learning using computational models. We compare two dominant paradigms in language learning: interactive learning and cross-situational learning - which differ primarily in the role of social feedback such as gaze or pointing. We analyze the relationship between these two paradigms and propose a new mixed paradigm that combines the two paradigms and allows to test algorithms in experiments that combine no feedback and social feedback. To deal with mixed feedback experiments, we develop new algorithms and show how they perform with respect to traditional knn and prototype approaches.
Originele taal-2English
Titel7th Joint IEEE International Conference on Development and Learning and on Epigenetic Robotics, ICDL-EpiRob 2017
UitgeverijIEEE Computational Intelligence Society
Pagina's221-226
Aantal pagina's6
Volume2018-January
ISBN van elektronische versie978-1-5386-3715-9
ISBN van geprinte versie978-1-5386-3715-9, 978-1-5386-3716-6
DOI's
StatusPublished - 2 apr 2018
Evenement2017 Joint IEEE International Conference on Development and Learning and Epigenetic Robotics - Congress Center of the Instituto Superior Tecnico , Lisbon, Portugal
Duur: 18 sep 201721 sep 2017

Publicatie series

Naam7th Joint IEEE International Conference on Development and Learning and on Epigenetic Robotics, ICDL-EpiRob 2017
Volume2018-January

Conference

Conference2017 Joint IEEE International Conference on Development and Learning and Epigenetic Robotics
Verkorte titelICDL-EpiRob
Land/RegioPortugal
StadLisbon
Periode18/09/1721/09/17

Vingerafdruk

Duik in de onderzoeksthema's van 'Computational Models of Tutor Feedback in Language Acquisition'. Samen vormen ze een unieke vingerafdruk.

Citeer dit