Difference between revisions of "Textual Entailment Portal"
Erel Segal (talk | contribs) m |
m (Reverted edits by Creek (talk) to last revision by StuartLaJoie) |
||
| (2 intermediate revisions by 2 users not shown) | |||
| Line 13: | Line 13: | ||
* hypothesis: ''Giving money to a poor man will make you better person''. | * hypothesis: ''Giving money to a poor man will make you better person''. | ||
| − | The entailment need not be pure logical - it has a more relaxed definition: "t entails h (t ⇒ h) if, typically, a human reading t would infer that h is most likely true."<ref>I. | + | The entailment need not be pure logical - it has a more relaxed definition: "t entails h (t ⇒ h) if, typically, a human reading t would infer that h is most likely true."<ref>[http://u.cs.biu.ac.il/~dagan/publications/RTEChallenge.pdf Ido Dagan, Oren Glickman and Bernardo Magnini. The PASCAL Recognising Textual Entailment Challenge, p. 2] ''in:'' Quiñonero-Candela, J.; Dagan, I.; Magnini, B.; d'Alché-Buc, F. (Eds.) ''Machine Learning Challenges. Lecture Notes in Computer Science'' , Vol. 3944, pp. 177-190, Springer, 2006.</ref> |
Recognizing Textual Entailment (RTE) has been proposed recently as a generic task that captures major semantic inference needs across many natural language processing applications. | Recognizing Textual Entailment (RTE) has been proposed recently as a generic task that captures major semantic inference needs across many natural language processing applications. | ||
| Line 21: | Line 21: | ||
* PASCAL Challenge - [[Recognizing Textual Entailment|Recognizing Textual Entailment (RTE)]] | * PASCAL Challenge - [[Recognizing Textual Entailment|Recognizing Textual Entailment (RTE)]] | ||
* [[Textual Entailment References]] - Workshops, Tutorials and Papers. | * [[Textual Entailment References]] - Workshops, Tutorials and Papers. | ||
| + | ==Notes== | ||
| + | <references/> | ||
[[Category:Textual Entailment Portal]] | [[Category:Textual Entailment Portal]] | ||
Revision as of 05:19, 25 June 2012
Textual Entailment (TE) is a directional relation between text fragments. The relation holds whenever the truth of one text fragment follows from another text. In the TE framework, the entailing and entailed texts are termed text and hypothesis, respectively.
An example of a positive TE (text entails hypothesis) is:
- text: If you help the needy, God will reward you.
- hypothesis: Giving money to a poor man has good consequences.
An example of a negative TE (text contradicts hypothesis) is:
- text: If you help the needy, God will reward you.
- hypothesis: Giving money to a poor man has no consequences.
An example of a non-TE (text does not entail nor contradict) is:
- text: If you help the needy, God will reward you.
- hypothesis: Giving money to a poor man will make you better person.
The entailment need not be pure logical - it has a more relaxed definition: "t entails h (t ⇒ h) if, typically, a human reading t would infer that h is most likely true."[1]
Recognizing Textual Entailment (RTE) has been proposed recently as a generic task that captures major semantic inference needs across many natural language processing applications.
This page serves as a community portal for everything related to Textual Entailment:
- Textual Entailment Resource Pool - Complete RTE Systems, RTE data sets, Knowledge Resources, Tools (Parsers, Role Labelling, Entity Recognition Tools, Similarity / Relatedness Tools, Corpus Readers, Related Libraries), Links.
- PASCAL Challenge - Recognizing Textual Entailment (RTE)
- Textual Entailment References - Workshops, Tutorials and Papers.
Notes
- ↑ Ido Dagan, Oren Glickman and Bernardo Magnini. The PASCAL Recognising Textual Entailment Challenge, p. 2 in: Quiñonero-Candela, J.; Dagan, I.; Magnini, B.; d'Alché-Buc, F. (Eds.) Machine Learning Challenges. Lecture Notes in Computer Science , Vol. 3944, pp. 177-190, Springer, 2006.