Recognizing Textual Entailment

author: Ido Dagan, Bar Ilan University

You might be experiencing some problems with Your Video player.

*Slides*
0:00	The PASCAL - Recognizing Textual Entailment
0:26	Recognizing Textual Entailment
0:50	The Second PASCAL Recognising Textual Entailment Challenge
1:34	The Third PASCAL Recognising Textual Entailment Challenge
2:25	RTE Motivation
4:09	Framework Desiderata
5:27	Outline
6:08	Natural Language and Meaning
7:08	Variability of Semantic Expression
8:17	Typical Application Inference
10:44	KRAQ'05 Workshop - KNOWLEDGE and REASONING for ANSWERING QUESTIONS
11:14	Classical Entailment Definition
12:04	“Almost certain” Entailments
12:34	Applied Textual Entailment
13:46	Evaluation Dataset
13:58	Generic Dataset by Application Use
16:11	Some Examples
18:30	psm08_dagan_rte_Page_18
19:36	Final Dataset (RTE-3)
19:50	Progress from 1 to 3
24:22	Suggested Perspective
25:19	Participating Systems
25:23	Participation
26:28	Methods and Approaches
29:45	Dominant approach: Supervised Learning
30:02	Methods and Approaches
30:09	Dominant approach: Supervised Learning
31:17	Parse-based Proof Systems
33:13	Resources
34:12	Accuracy Results – RTE-1
34:27	Results: RTE-2
34:53	Results: RTE-3
35:00	Current Limitations
35:42	Impact
37:11	New Potentials for Machine Learning
37:19	Classical Approach = Interpretation
38:40	Textual Entailment = Text Mapping
39:03	General Case – Inference
40:27	Machine Learning Perspectives
42:06	Major Learning Directions
42:57	Learning Entailment Knowledge
44:33	Meeting the knowledge challenge – by a coordinated effort?
44:54	Textual Entailment ≈ Human Reading Comprehension
46:04	Where are we (from RTE-1)?
46:26	Cautious Optimism
46:34	- Questions

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.