Incorporating Prior Knowledge into NLP with Markov Logic

author: Pedro Domingos, Dept. of Computer Science & Engineering, University of Washington

You might be experiencing some problems with Your Video player.

*Slides*
0:00	Incorporating Prior Knowledge into NLP with Markov Logic
0:32	Overview - Motivation
0:57	Language and Knowledge:The Chicken and the Egg
2:47	What’s Needed for This to Work?
5:10	Markov Logic
6:13	Overview - Background
6:21	Markov Networks - 1
7:28	Markov Networks - 2
7:49	Markov Networks - 1
7:50	Markov Networks - 2
8:08	Markov Networks - 1
8:19	Markov Networks - 2
8:27	Markov Networks - 1
8:35	Markov Networks - 2
8:38	First-Order Logic
9:53	Overview - Markov Logic
9:55	Markov Logic
11:01	Definition
11:42	Example: Friends & Smokers - 1
11:54	Example: Friends & Smokers - 2
12:10	Example: Friends & Smokers - 1
12:12	Example: Friends & Smokers - 2
12:23	Example: Friends & Smokers - 3
12:41	Example: Friends & Smokers - 4
12:49	Example: Friends & Smokers - 5
12:52	Example: Friends & Smokers - 6
13:09	Example: Friends & Smokers - 7
13:17	Example: Friends & Smokers - 8
13:25	Markov Logic Networks
14:08	Relation to Statistical Models
15:11	Relation to First-Order Logic
16:16	Overview - Inference
16:21	Belief Propagation - 1
17:09	Belief Propagation - 2
17:27	Belief Propagation - 3
17:32	Belief Propagation - 4
17:40	But This Is Too Slow
18:36	Belief Propagation - 5
18:43	Lifted Belief Propagation - 1
19:10	Lifted Belief Propagation - 2
19:47	Lifted Belief Propagation - 3
20:28	Forming the Lifted Network
21:42	Overview - Learning
21:46	Learning
22:43	Weight Learning
23:32	Voted Perceptron
24:29	Voted Perceptron for MLNs
24:54	Overview - Applications
24:57	Information Extraction
25:11	Segmentation
25:16	Entity Resolution - 1
25:30	Entity Resolution - 2
25:39	State of the Art
26:43	Types and Predicates - 1
26:51	Types and Predicates - 2
27:06	Types and Predicates - 3
27:15	Types and Predicates - 4
27:38	Formulas - 1
27:41	Formulas - 2
28:32	Formulas - 3
28:46	Formulas - 4
29:14	Formulas - 5
29:52	Formulas - 6
30:50	Formulas - 7
31:31	Formulas - 8
32:51	Results: Segmentation on Cora
33:44	Other Examples
36:03	Overview - Discussion
36:09	Next Steps
37:29	Conclusion
40:35	- 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.