Referential Uncertainty and Word Learning in High-Dimensional, Continuous Meaning Spaces

Michael Spranger, Katrien Beuls

Onderzoeksoutput: Conference paper

Samenvatting

This paper discusses lexicon word learning in high-dimensional
meaning spaces from the viewpoint of referential uncertainty. We investigate
various state-of-the-art Machine Learning algorithms and discuss the impact
of scaling, representation and meaning space structure. We demonstrate that
current Machine Learning techniques successfully deal
with high-dimensional meaning spaces. In particular, we show that exponentially
increasing dimensions linearly impact learner performance and
that referential uncertainty from word sensitivity has no impact.
Originele taal-2English
Titel6th International Conference on Development and Learning and on Epigenetic Robotics
Pagina's95-100
Aantal pagina's6
ISBN van elektronische versie2161-9484
StatusPublished - 2016
EvenementThe Sixth Joint IEEE International Conference on Developmental Learning and Epigenetic Robotics - Cergy-Pontoise, France
Duur: 19 sep 201622 sep 2016
Congresnummer: 6
http://www.etis.ensea.fr/neurocyber/ICDL-EPIROB2016/home.php

Conference

ConferenceThe Sixth Joint IEEE International Conference on Developmental Learning and Epigenetic Robotics
Verkorte titelIEEE ICDL-EPIROB
Land/RegioFrance
StadCergy-Pontoise
Periode19/09/1622/09/16
Internet adres

Vingerafdruk

Duik in de onderzoeksthema's van 'Referential Uncertainty and Word Learning in High-Dimensional, Continuous Meaning Spaces'. Samen vormen ze een unieke vingerafdruk.

Citeer dit