Normalized Alignment of Dependency Trees for Detecting Textual Entailment thumbnail
Pause
Mute
Subtitles
Playback speed
0.25
0.5
0.75
1
1.25
1.5
1.75
2
Full screen

Normalized Alignment of Dependency Trees for Detecting Textual Entailment

Published on Feb 25, 20072967 Views

In this paper, we investigate the usefulness of normalized alignment of dependency trees for entailment prediction. Overall, our approach yields an accuracy of 60% on the RTE2 test set, which is a sig

Related categories

Chapter list

Normalized alignment of dependency trees for detecting textual entailment00:01
Basic idea00:40
Matching surface words alone is not sufficient...01:11
Preprocessing02:08
Syntactic Normalization02:27
Auxiliary Reduction02:44
Passive to Active Form03:54
Copula Reduction04:09
Alignment of Dependency Trees04:20
Word Matching05:03
Alignment example05:20
Alignment example (cont’d)05:45
Entailment prediction06:31
Results06:41
Problems06:54
Discussion & Conclusion07:44