Recognizing Textual Entailment with LCC´s GROUNDHOG System

author: Andrew Hickl, Language Computer Corporation, Richardson, Texas

Description

We introduce a new system for recognizing textual entailment (known as GROUNDHOG) which utilizes a classification-based approach to combine lexico-semantic information derived from text processing applications with a large collection of paraphrases acquired automatically from the WWW. Trained on 200,000 examples of textual entailment extracted from newswire corpora, our system managed to classify more than 75% of the pairs in the 2006 PASCAL RTE Test Set correctly.

Categories

Top: Computer Science: Natural Language Processing
Top: Computer Science: Text Mining

You might be experiencing some problems with Your Video player.

*Slides*
0:00	Recognizing Textual Entailment with LCC’s Groundhog System
1:07	Introduction
1:55	Outline of Today’s Talk
2:19	Architecture of the Groundhog System
3:35	A Motivating Example
5:39	Preprocessing
6:46	Preprocessing
7:34	Preprocessing
7:49	Preprocessing
8:32	Preprocessing
9:24	Preprocessing
10:08	Preprocessing
11:16	Preprocessing
11:27	Lexical Alignment
12:25	Lexical Alignment
13:09	Lexical Alignment
13:57	Training the Alignment Classifier
14:33	Creating New Sources of Training Data
15:39	Creating New Sources of Training Data
16:53	Training the Alignment Classifier
17:35	Paraphrase Acquisition
19:11	Paraphrase Acquisition
19:44	Paraphrase Acquisition
20:45	Entailment Classification
21:27	Entailment Classification
22:24	Entailment Classification
24:53	Entailment Classification
26:10	Another Example
26:40	Example 734
28:27	Evaluation: 2006 RTE Performance
30:05	Evaluation: Role of Training Data
31:23	Evaluation: Role of Features in Entailment Classifier
32:42	Conclusions

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.