COGEX at the Second Recognizing Textual Entailment Challenge

author: Marta Tatu, Language Computer Corporation, Richardson, Texas

Description

This paper proposes a knowledge representation model and a logic proving setting with axioms on demand which proved to be very successful for the recognizing textual entailment task. LCC´s submission to the Second RTE Challenge exploits the logical entailment between deep semantics and syntax of T and H as well as a shallow lexical alignment of the two texts.

You might be experiencing some problems with Your Video player.

*Slides*
0:00	COGEX at the Second RTE
0:18	LCC’s Submission to RTE2
2:09	Approach to RTE with COGEX
5:01	COGEX Enhancements (1/3)
6:30	COGEX Enhancements (1/3)
7:10	COGEX Enhancements (1/3)
8:29	Logic Forms Differences
9:32	Logic Forms Differences
10:26	COGEX Enhancements (2/3)
11:59	COGEX Enhancements (2/3)
12:56	More Axioms
14:25	COGEX Enhancements (3/3)
16:46	Shallow Lexical Alignment
17:55	Results
21:20	Results, Future Work
22:44	Thank You !
24:10	Approach to RTE with COGEX

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.