0.25
0.5
0.75
1.25
1.5
1.75
2
Recognizing Textual Entailment with LCC´s GROUNDHOG System
Published on Feb 25, 20075938 Views
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 app
Related categories
Chapter list
Recognizing Textual Entailment with LCC’s Groundhog System00:00
Introduction01:07
Outline of Today’s Talk01:55
Architecture of the Groundhog System02:19
A Motivating Example03:35
Preprocessing05:39
Preprocessing06:46
Preprocessing07:34
Preprocessing07:49
Preprocessing08:32
Preprocessing09:24
Preprocessing10:08
Preprocessing11:16
Lexical Alignment11:27
Lexical Alignment12:25
Lexical Alignment13:09
Training the Alignment Classifier13:57
Creating New Sources of Training Data14:33
Creating New Sources of Training Data15:39
Training the Alignment Classifier16:53
Paraphrase Acquisition17:35
Paraphrase Acquisition19:11
Paraphrase Acquisition19:44
Entailment Classification20:45
Entailment Classification21:27
Entailment Classification22:24
Entailment Classification24:53
Another Example26:10
Example 73426:40
Evaluation: 2006 RTE Performance28:27
Evaluation: Role of Training Data30:05
Evaluation: Role of Features in Entailment Classifier31:23
Conclusions32:42