Home

About

Advanced Search

Browse by Discipline

Scientific Societies

E-print Alerts

Add E-prints

E-print Network
FAQHELPSITE MAPCONTACT US


  Advanced Search  

 
ToappearinProceedingsofthe30thAnnualConferenceoftheCognitiveScienceSociety(CogSci2008),Washington,D.C. A Probabilistic Incremental Model of Word Learning in the Presence of
 

Summary: ToappearinProceedingsofthe30thAnnualConferenceoftheCognitiveScienceSociety(CogSci2008),Washington,D.C.
A Probabilistic Incremental Model of Word Learning in the Presence of
Referential Uncertainty
Afsaneh Fazly, Afra Alishahi and Suzanne Stevenson
Department of Computer Science
University of Toronto
{afsaneh,afra,suzanne}@cs.toronto.edu
Abstract
We present a probabilistic incremental model of early word
learning. The model acquires the meaning of words from ex-
posure to word usages in sentences, paired with appropriate
semantic representations, in the presence of referential uncer-
tainty. A distinct property of our model is that it continually re-
vises its learned knowledge of a word's meaning, but over time
converges on the most likely meaning of the word. Another
key feature is that the model bootstraps its own partial knowl-
edge of word­meaning associations to help more quickly learn
the meanings of novel words. Results of simulations on nat-
uralistic child-directed data show that our model exhibits be-
haviours similar to those observed in the early lexical acquisi-

  

Source: Alishahi, Afra - Department of Computational Linguistics and Phonetics, Universität des Saarlandes

 

Collections: Computer Technologies and Information Sciences