Learning to Reason Knowledge Acquisition in Cyc

author: Michael Witbrock, Cycorp Inc.

Categories

Top: Computer Science: Semantic Web: Ontologies

You might be experiencing some problems with Your Video player.

*Slides*
0:00	Learning to Reason: Knowledge Acquisition in Cyc
0:41	Overview
1:09	Expressivity
1:14	The Cyc Knowledge Base
2:54	Syntactic Power
3:55	For Inference: Senses of ‘In’
5:05	Senses of ‘In’
5:44	Concepts are densely related
6:23	in Cyc
7:20	Power
7:55	The Cyc Analytic Environment - 1
8:44	The Cyc Analytic Environment - 2
9:15	How is this done?
12:12	The Cyc Analytic Environment - 3
12:52	45th’s Space Wing Hurricane Preparedness
13:23	Performance: Subtheory: disjointWith
14:25	Inference is Fast & Trainable
15:05	You can get Cyc
17:15	Cycorp Corporate Mission
18:30	Manual Knowledge Entry
19:36	Cycorp Corporate Mission
21:10	Ambitious Approach: General Automated Interview - 2
21:44	Ambitious Approach: General Automated Interview - 1
21:58	Ambitious Approach: General Automated Interview - 2
22:04	Ambitious Approach: Analogical Reasoning
22:12	Ambitious Approach: Using Background Knowledge
22:31	Concept Refinement Interview
22:55	Ambition is Good but...
25:09	What can you do?
27:23	Example: Getting Knowledge in Context
30:03	Example: Use of Acquired Knowledge - 1
31:05	Example: Use of Acquired Knowledge - 2
31:27	Example: Use of Acquired Knowledge - 3
31:58	Example: Use of Acquired Knowledge - 4
32:56	Intelligent Search
34:10	Content adaptation: heart valve repair
34:34	Content adaptation: coronary artery
34:59	Facts and Rules (from 1998, 2003)
35:37	Some opportunities for ML
36:14	Document Tagging
36:51	Military Taxonomy
38:10	Knowledge-based disambiguation - 1
38:59	Disambiguation Rules: ‘Jet’
40:01	Knowledge-based disambiguation - 2
41:39	Knowledge Driven Disambiguation - 1
42:51	Rule Induction
43:06	The Induction Pipeline
43:43	Example - 1
44:45	Example - 2
46:15	Early Results
48:02	Sample Rules Produced
48:28	Situation Recognition
51:49	Example - 1
52:14	Example - 2
52:44	Example - 3
54:35	Example - 4
55:34	Other Approaches
56:11	Previous Results on Whodunit Task
56:41	Integrating Markov Logic
57:33	Early ML Experiments
58:06	Markov Logic Work
58:47	Getting Ground Facts
60:36	Second Life
61:40	Overview
61:55	- 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.