High-coverage extraction of semantic assertions from text thumbnail
slide-image
Pause
Mute
Subtitles not available
Playback speed
0.25
0.5
0.75
1
1.25
1.5
1.75
2
Full screen

High-coverage extraction of semantic assertions from text

Published on Nov 04, 20113049 Views

We present an early version of a method for open-domain semantic assertion extraction from natural language texts. To combat the shortage of training data for the task, a two-stage pipeline is employe

Related categories

Chapter list

High-Coverage Extraction of Semantic Assertions from Text00:00
The Task00:17
This is a sad panda01:03
The Compromise01:37
Background Knowledge02:22
Ontology: CYC02:29
The Glue: FrameNet03:11
FrameNet and Cyc04:44
Semantic Role Labeling (SRL)05:03
SRL: Standard Breakdown into Tasks05:13
SRL: Role Detection and Classification06:41
Mapping: FrameNet -> Cyc07:40
Mapping Frames07:41
Mapping Roles08:11
Mapping Role-Fillers08:50
Results09:36
Results: the Numbers09:38
Results: an Example10:24
Questions?11:46