Learning in wubble world

Wesley Kerr, Shane Hoversten, Daniel Hewlett, Paul R Cohen, Yu Han Chang

Research output: Chapter in Book/Report/Conference proceedingConference contribution

4 Citations (Scopus)

Abstract

Why do children master language so quickly and thoroughly, whereas gigabytes of text and enormously sophisticated learning algorithms produce at best shallow semantics in machines? Because children have help from competent speakers who relate language to what's happening in the child's environment. To facilitate the task of machine word learning, we developed a simulated environment, called "Wubble World," and populated it with entities called wubbles. Children interact with the wubbles using natural language, and act as teachers when the wubble needs help. This paper presents our word learning algorithms and provides some empirical results.

Original languageEnglish (US)
Title of host publication2007 IEEE 6th International Conference on Development and Learning, ICDL
Pages330-335
Number of pages6
DOIs
StatePublished - 2007
Externally publishedYes
Event2007 IEEE 6th International Conference on Development and Learning, ICDL - London, United Kingdom
Duration: Jul 11 2007Jul 13 2007

Other

Other2007 IEEE 6th International Conference on Development and Learning, ICDL
CountryUnited Kingdom
CityLondon
Period7/11/077/13/07

Fingerprint

Learning algorithms
Semantics

Keywords

  • Development
  • Language
  • Online learning
  • Semantics
  • Virtual environment

ASJC Scopus subject areas

  • Computational Theory and Mathematics
  • Computer Science Applications

Cite this

Kerr, W., Hoversten, S., Hewlett, D., Cohen, P. R., & Chang, Y. H. (2007). Learning in wubble world. In 2007 IEEE 6th International Conference on Development and Learning, ICDL (pp. 330-335). [4354034] https://doi.org/10.1109/DEVLRN.2007.4354034

Learning in wubble world. / Kerr, Wesley; Hoversten, Shane; Hewlett, Daniel; Cohen, Paul R; Chang, Yu Han.

2007 IEEE 6th International Conference on Development and Learning, ICDL. 2007. p. 330-335 4354034.

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Kerr, W, Hoversten, S, Hewlett, D, Cohen, PR & Chang, YH 2007, Learning in wubble world. in 2007 IEEE 6th International Conference on Development and Learning, ICDL., 4354034, pp. 330-335, 2007 IEEE 6th International Conference on Development and Learning, ICDL, London, United Kingdom, 7/11/07. https://doi.org/10.1109/DEVLRN.2007.4354034
Kerr W, Hoversten S, Hewlett D, Cohen PR, Chang YH. Learning in wubble world. In 2007 IEEE 6th International Conference on Development and Learning, ICDL. 2007. p. 330-335. 4354034 https://doi.org/10.1109/DEVLRN.2007.4354034
Kerr, Wesley ; Hoversten, Shane ; Hewlett, Daniel ; Cohen, Paul R ; Chang, Yu Han. / Learning in wubble world. 2007 IEEE 6th International Conference on Development and Learning, ICDL. 2007. pp. 330-335
@inproceedings{64b3c7a8258d4c23a0224199f9e4afe7,
title = "Learning in wubble world",
abstract = "Why do children master language so quickly and thoroughly, whereas gigabytes of text and enormously sophisticated learning algorithms produce at best shallow semantics in machines? Because children have help from competent speakers who relate language to what's happening in the child's environment. To facilitate the task of machine word learning, we developed a simulated environment, called {"}Wubble World,{"} and populated it with entities called wubbles. Children interact with the wubbles using natural language, and act as teachers when the wubble needs help. This paper presents our word learning algorithms and provides some empirical results.",
keywords = "Development, Language, Online learning, Semantics, Virtual environment",
author = "Wesley Kerr and Shane Hoversten and Daniel Hewlett and Cohen, {Paul R} and Chang, {Yu Han}",
year = "2007",
doi = "10.1109/DEVLRN.2007.4354034",
language = "English (US)",
isbn = "1424411165",
pages = "330--335",
booktitle = "2007 IEEE 6th International Conference on Development and Learning, ICDL",

}

TY - GEN

T1 - Learning in wubble world

AU - Kerr, Wesley

AU - Hoversten, Shane

AU - Hewlett, Daniel

AU - Cohen, Paul R

AU - Chang, Yu Han

PY - 2007

Y1 - 2007

N2 - Why do children master language so quickly and thoroughly, whereas gigabytes of text and enormously sophisticated learning algorithms produce at best shallow semantics in machines? Because children have help from competent speakers who relate language to what's happening in the child's environment. To facilitate the task of machine word learning, we developed a simulated environment, called "Wubble World," and populated it with entities called wubbles. Children interact with the wubbles using natural language, and act as teachers when the wubble needs help. This paper presents our word learning algorithms and provides some empirical results.

AB - Why do children master language so quickly and thoroughly, whereas gigabytes of text and enormously sophisticated learning algorithms produce at best shallow semantics in machines? Because children have help from competent speakers who relate language to what's happening in the child's environment. To facilitate the task of machine word learning, we developed a simulated environment, called "Wubble World," and populated it with entities called wubbles. Children interact with the wubbles using natural language, and act as teachers when the wubble needs help. This paper presents our word learning algorithms and provides some empirical results.

KW - Development

KW - Language

KW - Online learning

KW - Semantics

KW - Virtual environment

UR - http://www.scopus.com/inward/record.url?scp=50849097847&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=50849097847&partnerID=8YFLogxK

U2 - 10.1109/DEVLRN.2007.4354034

DO - 10.1109/DEVLRN.2007.4354034

M3 - Conference contribution

SN - 1424411165

SN - 9781424411160

SP - 330

EP - 335

BT - 2007 IEEE 6th International Conference on Development and Learning, ICDL

ER -