Machine Learning and Cognitive Science of Language Acquisition

Bayesian models of cross-situational word learning

author: Michael Frank, Department of Brain and Cognitive Sciences, MIT - Massachusetts Institute of Technology

You might be experiencing some problems with Your Video player.

*Slides*
0:00	Bayesian models of cross-situational word learning
0:10	Word-learning in action
0:58	The problem of word learning
1:34	One possible solution
2:10	The problem of word learning
3:17	Outline
4:05	Three facts of word learning
6:26	Three facts of word learning
6:36	Outline•Our model: Bayesian word-learner
7:38	Generative model: example
9:39	Inference
10:35	Corpus
11:39	Model comparison
12:58	Results: model comparison
15:32	Results: intuitive analysis
16:08	Outline•Extension: Learning social cues
16:21	Social corpus coding
16:44	How it works
17:14	Social model framework
17:44	Preliminary Results
18:52	Outline •Experimental coverage
19:02	Mutual exclusivity
21:57	Fast-mapping
23:07	Use of social cues
24:11	Conclusions

Lecture rating

People found this lecture:
Worth seeing
because it is:
Valuable and informative
Well presented
Easily understandable
Acceptably recorded
You need to login to cast your vote.

Report a problem or upload files

If you have found a problem with this lecture or would like to send us extra material, articles, exercises, etc., please use our ticket system to describe your request and upload the data.
Enter your e-mail into the 'Cc' field, and we will keep you updated with your request's status.