English
 
User Manual Privacy Policy Disclaimer Contact us
  Advanced SearchBrowse

Item

ITEM ACTIONSEXPORT

Released

Conference Paper

Modelling novelty preference in word learning

MPS-Authors
/persons/resource/persons41922

Versteegh,  Maarten
International Max Planck Research School for Language Sciences, MPI for Psycholinguistics, Max Planck Society, Nijmegen, NL;
Centre for Language Studies · Radboud University Nijmegen;

Locator
There are no locators available
Fulltext (public)

Versteegh_Interspeech_2011.pdf
(Publisher version), 359KB

Supplementary Material (public)
There is no public supplementary material available
Citation

Versteegh, M., Ten Bosch, L., & Boves, L. (2011). Modelling novelty preference in word learning. In Proceedings of the 12th Annual Conference of the International Speech Communication Association (Interspeech 2011), Florence, Italy (pp. 761-764).


Cite as: http://hdl.handle.net/11858/00-001M-0000-000F-8286-A
Abstract
This paper investigates the effects of novel words on a cognitively plausible computational model of word learning. The model is first familiarized with a set of words, achieving high recognition scores and subsequently offered novel words for training. We show that the model is able to recognize the novel words as different from the previously seen words, based on a measure of novelty that we introduce. We then propose a procedure analogous to novelty preference in infants. Results from simulations of word learning show that adding this procedure to our model speeds up training and helps the model attain higher recognition rates.