Learning Textual Entailment from Examples

author: Fabio Massimo Zanzotto, University of Milano - Bicocca

Description

In this paper we present a novel approach for learning entailment relations from positive and negative examples. We define a similarity between two text-hypothesis pairs based on a syntatic and lexical information. We experimented our model within the RTE 2006 challenge obtaining the accuracy of 63.88and 62.50% for the two submissions.

You might be experiencing some problems with Your Video player.

*Slides*
0:01	Learning Textual Entailment from Examples
0:39	Motivating the approach (1)
2:08	Motivating the approach (2)
3:27	Our Model
4:18	Outline
4:41	Challenges for the cross-pair similarity (1)
5:09	Challenges for the cross-pair similarity (2)
6:48	Challenges for the cross-pair similarity (3)
7:11	Our Model: an example
7:31	Our Model: an example
7:33	Our Model: an example
7:42	Our Model: an example
7:51	Our Model: an example
8:01	Our Model: an example
8:11	Our Model: an example
8:16	Our Model: an example
8:21	Our Model: an example
8:34	Our Model: an example
9:46	Our Model: an example
10:47	Similarity Models
11:00	Anchoring and Intra-pair Lexical Similarity
12:04	Anchoring and Intra-pair Lexical Similarity
13:23	Cross-pair similarity
15:12	Refining Cross-pair Similarity
16:10	Experimental Setting
17:37	Experimental Results
21:43	Conclusions
23:27	slide28

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.