Toward Dependency Path based Entailment

author: Rodney D. Nielsen, University of Colorado

Description

We present our submission to the RTE2 challenge which takes steps in the direction of dynamically entailing hypotheses via their dependency paths. We evaluate semantic similarity between sentences utilizing corpus co-occurence estimates of various dependency path features and show a 2.7% improvement on the RTE1 dataset.

You might be experiencing some problems with Your Video player.

*Slides*
0:01	Toward Dependency Path based Entailment
0:22	Dependency Path-based Entailment
1:23	ML Classification Approach
2:14	Corpora
2:26	Core Features
3:07	Dependency Features
4:38	Dependency Features
4:58	Dependency Features
5:37	Dependency Features
6:26	Dependency Features
6:47	Verb Dependency Features
7:11	Subject Dependency Features
7:45	Other Dependency Features
8:01	Results
10:04	Feature Analysis
10:53	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.