Textual Entailment as Syntactic Graph Distance: a rule based and a SVM based approach

author: Fabio Massimo Zanzotto, University of Milano - Bicocca

Categories

Top: Computer Science: Machine Learning: Kernel Methods: Support Vector Machines

You might be experiencing some problems with Your Video player.

*Slides*
0:04	Textual Entailment as Syntactic Graph Distance: a rule based and a SVM based approach
0:30	Classifying Textual Entailment (TE)
3:05	Recognizing Textual Entailment (TE)
3:43	Graph Matching (GM)
4:28	Textual Entailment as Graph Matching (GM)
6:19	What’s next
7:09	Extended Dependency Graph (XDG)
8:34	GM on XDG: definitions
11:20	Finding the bijective function and evaluating the measure
11:43	Constituent Similarity
13:28	Dependency Similarity
14:36	Textual Entailment Measure
15:18	Some more details
16:01	Estimating Parameters with SVM
17:06	Feature Spaces
17:25	Feature Spaces
18:33	Used Resources
19:15	Preliminary analysis (Rule-based System)
20:07	Preliminary analysis (SVM-based system)
21:11	Out from the Fairy Tale...
22:08	... and back to real life!!!!

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.