Bayesian Modeling of Dependency Trees Using Hierarchical Pitman-Yor Priors

author: Hanna M. Wallach, Department of Computer Science, University of Massachusetts Amherst

You might be experiencing some problems with Your Video player.

*Slides*
0:00	Bayesian Models for Dependency Parsing Using Pitman-Yor Priors
0:14	Dependency Parsing - 1
0:34	Dependency Parsing - 2
0:45	Dependency Parsing - 3
1:20	Talk Outline
1:54	Eisner's Generative Dependency Model - 1
2:30	Eisner's Generative Dependency Model - 2
2:37	Eisner's Generative Dependency Model - 3
2:59	Eisner's Generative Dependency Model - 4
3:12	Eisner's Generative Dependency Model - 5
3:17	Eisner's Generative Dependency Model - 6
3:31	Eisner's Generative Dependency Model - 7
3:38	Eisner's Generative Dependency Model - 8
3:44	Eisner's Generative Dependency Model - 9
3:48	Eisner's Generative Dependency Model - 10
3:52	Eisner's Generative Dependency Model - 11
3:59	Generating a Tagged, Cased Word - 1
4:33	Generating a Tagged, Cased Word - 2
5:03	Generating a Tagged, Cased Word - 3
5:23	Generating a Tagged, Cased Word - 4
5:41	Estimating Probabilities from Data - 1
7:18	Estimating Probabilities from Data - 2
8:43	Estimating Probabilities from Data - 3
8:52	Estimating Probabilities from Data - 4
9:01	Estimating Probabilities from Data - 5
9:13	Contexts for Tags and Uncased Words
10:00	A Hierarchical Bayesian Dependency Model
11:31	Base Measures
12:24	Predictive Distributions
13:27	Relationship to Eisner's Model
13:47	Advantages of the Bayesian Reinterpretation
14:31	Using Hierarchical Pitman-Yor Priors
15:52	Pitman-Yor Predictive Distributions
16:37	Relationship to Bayesian n-gram Language Modeling
17:29	Using the Model
18:28	Parsing Experiments
19:24	Results: Parse Accuracy
20:58	Latent Variable Parsing Models
22:24	First Order Models
22:35	"Syntactic" Latent Variables - 1
22:57	"Syntactic" Latent Variables - 2
23:06	"Syntactic" Latent Variables - 3
23:15	"Syntactic" Latent Variables - 4
23:20	"Syntactic" Latent Variables - 5
23:36	"Syntactic" Latent Variables - 6
23:43	"Syntactic" Latent Variables - 7
23:51	"Syntactic" Latent Variables - 8
23:53	"Syntactic Topics": Parse Accuracy
25:18	States Inferred from Treebank Sections 2-21
26:02	Unsupervised Leave-One-Out Bits-Per-Word
27:05	Conclusions and Future Work
27:43	Questions?
28:16	- Questions

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.