Workshop on Machine Learning and Cognitive Science of Language Acquisition, London 2007

Latent Semantic Grammar Induction

author: Andrew Olney, Department of Psychology, University of Memphis
published: Oct. 31, 2007, recorded: June 2007, views: 308

Slides

Slides
0:00	Latent Semantic Grammar Induction
0:09	Supervised Grammar Induction
0:28	Unsupervised Grammar Induction
1:14	Basic Model
1:58	Distributional Analysis
2:32	Substitutability
3:00	Context - part 1
3:48	Context - part 2
4:40	Singular value decomposition
6:18	Context - part 2
6:20	Context - part 1
6:33	Singular value decomposition
6:36	Search
8:20	Populating the Graph - part 1
8:50	Populating the Graph - part 2
9:13	Populating the Graph - part 3
9:57	Populating the Graph - part 4
11:33	Populating the Graph - part 5
11:38	Populating the Graph - part 6
11:52	Populating the Graph - part 7
11:53	Populating the Graph - part 8
11:54	Populating the Graph - part 9
12:25	Solving the Graph - part 1
12:50	Solving the Graph - part 2
13:27	Solving the Graph - part 3
13:44	Solving the Graph - part 4
14:26	Solving the Graph - part 5
15:23	Solving the Graph - part 6
15:36	Solving the Graph - part 7
16:52	Materials
18:29	Baselines
19:21	Prior Knowledge - part 1
20:21	Prior Knowledge - part 2
21:38	Conclusions

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.

Lecture popularity: You need to login to cast your vote.

Description

Supervised Grammar Induction works great but is expensive, time consuming and area specific. Unsupervised Grammar Induction is a more general solution, can explore knowledge required: OS/hidden syntax, projectivity, prior distributions, semantics.