Using Maximal Embedded Syntatic Subtrees for Textual Entailment Recognition

author: Sophia Katrenko, University of Amsterdam

Description

In this paper we address the textual entailment task by using tree mining and matching technique. Our results show that accuracy can be improved when using a combination of lexical entailment with syntactic matching. The best result we received by combinig two components is the following: 70% of recall and 57,5% of precision on the test set.

You might be experiencing some problems with Your Video player.

*Slides*
0:01	Using Maximal Embedded Subtrees for Textual Entailment Recognition
1:13	Outline
1:25	Why trees?…
2:39	Motivation
3:07	What type of trees? (1)
3:40	What type of trees?(2)
5:16	Methodology
5:38	Data preprocessing
6:22	Syntactic matching
7:02	Runs
7:59	Official results (accuracy)
8:22	Precision vs. Recall
9:02	Precision vs. Recall (2)
9:37	Conclusions: Does it work?
10:07	Possible extensions
10:27	slide16

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.