Approaching Textual Entailment with LFG and FrameNet Frames

author: Aljoscha Burchardt, Saarland University

Description

We present a baseline system for modeling textual entailment that combines deep syntactic analysis with structured lexical meaning descriptions in the FrameNet paradigm. Textual entailment is approximated by degrees of structural and semantic overlap of text and hypothesis, which we measure in a match graph. The encoded measures of similarity are processed in a machine learning setting.

Categories

Top: Computer Science: Semantic Web

You might be experiencing some problems with Your Video player.

*Slides*
0:03	Approximating Textual Entailment with LFG and FrameNet Frames
0:47	Outline of this Talk
0:54	Frame Semantics (Fillmore 1976, Fillmore et. al. 2003)
1:28	Linguistic Normalizations (Frame: Commerce_buy)
2:46	Frame Semantics for RTE
3:29	A Baseline System for Approximating Textual Entailment
4:02	A Baseline System for Approximating Textual Entailment
5:05	Linguistic Components
6:33	Example from RTE 2006
7:07	LFG F-Structures
7:28	Automatic Frame Annotation for Text (SALTO Viewer)
9:00	Automatic Frame Annotation for Hypothesis
9:29	LFG + Frames for Hypothesis (FEFViewer)
10:07	Hypothesis-Text-Match Graphs Computing Structural and Semantic overlap
10:28	t: In 1983, Aki Kaurismäki directed his first full-time feature.
10:52	Statistical Modeling

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.