Machine Learning and Cognitive Science of Language Acquisition

An annotated hierarchies model of syntactic categories

author: Virginia Savova, Computational Cognitive Science Group, Department of Brain and Cognitive Sciences, MIT

Description

The role of syntactic categories (part-of-speech tags) in linguistic description: hierarchical organization of categories; factors in syntactic categorization. Presents a computational model for induction of hierarchical structure from relational and feature data. Presents the results of the application of the model to relational and feature data obtained from natural and artificial corpora.

You might be experiencing some problems with Your Video player.

*Slides*
0:00	Annotated Hierarchies Model for Syntactic Categories
0:13	Outline
1:28	Syntactic categories in linguistic description - part 1
2:26	Syntactic categories in linguistic description - part 2
3:24	Syntactic categories in linguistic description - part 3
4:00	Syntactic categories in linguistic description - part 4
5:19	Syntactic categories in linguistic description - part 5
5:38	Syntactic categories in linguistic description - part 6
6:16	Inducing an annotated hierarchy of SC
7:00	Annotated Hierarchies Model - part 1
8:23	Annotated Hierarchies Model - part 2
9:25	Experiment 1:The annotated hierarchy of X-bar theory - part 1
11:46	Experiment 1:The annotated hierarchy of X-bar theory - part 2
12:44	Experiment 1:The annotated hierarchy of X-bar theory - part 3
14:25	Experiment 1:The annotated hierarchy of X-bar theory - part 4
14:42	Experiment 1:The annotated hierarchy of X-bar theory - part 3
14:48	Experiment 1:The annotated hierarchy of X-bar theory - part 4
15:28	...but the real world is not as neat
15:32	Trees induced from BNC data
16:41	Experiment 2: BNC - part 1
17:59	Experiment 2: BNC - part 2
18:49	Experiment 2: BNC - part 3
19:15	Experiment 3: BNC - part 1
20:05	Experiment 3: BNC - part 2
20:39	Experiment 3: BNC - part 3
21:08	AH versus HC
22:04	Desired improvements to the AH model
24:00	Conclusion

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.