A Bayesian framework for cross-situational word-learning
Name
3165-a-bayesian-framework-for-cross-situational-word-learning.pdf
Size
330.31 KB
Format
Adobe PDF
Checksum (MD5)
12e9199a75a3623f01f993cbd0d7b969
Author(s)
Goodman, Noah Daniel
Tenenbaum, Joshua B
Frank, Michael C.
Date Issued
December 2007
Journal
Advances in Neural Information Processing Systems 20 (NIPS 2007)
Publisher
Neural Information Processing Systems Foundation
Citation
Frank, Michael C., Noah D. Goodman, and Joshua B. Tenenbaum. "A Bayesian Framework for Cross-Situational Word-Learning." Advances in Neural Information Processing Systems 20 (NIPS 2007), Vancouver, British Columbia, Canada, 3-8 December, 2007. © 2007 Neural Information Processing Systems Foundation
Version
Final published version
Abstract
For infants, early word learning is a chicken-and-egg problem. One way to learn a word is to observe that it co-occurs with a particular referent across different situations. Another way is to use the social context of an utterance to infer the intended referent of a word. Here we present a Bayesian model of cross-situational word learning, and an extension of this model that also learns which social cues are relevant to determining reference. We test our model on a small corpus of mother-infant interaction and find it performs better than competing models. Finally, we show that our model accounts for experimental phenomena including mutual exclusivity, fast-mapping, and generalization from social cues.
MIT Department
Massachusetts Institute of Technology. Department of Brain and Cognitive Sciences
Terms of Use
Article is made available in accordance with the publisher's policy and may be subject to US copyright law. Please refer to the publisher's site for terms of use.
Persistent DSpace Link
DOI of Published Version
https://papers.nips.cc/paper/3165-a-bayesian-framework-for-cross-situational-word-learning
