An inference model for semantic entailment in natural language

Rodrigo De Salvo Braz; Corina R Girju; Vasin Punyakanok; Dan Roth; Mark Sammons

An inference model for semantic entailment in natural language

Rodrigo De Salvo Braz, Corina R Girju, Vasin Punyakanok, Dan Roth, Mark Sammons

Research output: Contribution to conference › Paper › peer-review

Abstract

Semantic entailment is the problem of determining if the meaning of a given sentence entails that of another. This is a fundamental problem in natural language understanding that provides a broad framework for studying language variability and has a large number of applications. This paper presents a principled approach to this problem that builds on inducing representations of text snippets into a hierarchical knowledge representation along with a sound optimization-based inferential mechanism that makes use of it to decide semantic entailment. A preliminary evaluation on the PASCAL text collection is presented.

Original language	English (US)
Pages	1043-1049
Number of pages	7
State	Published - 2005
Event	20th National Conference on Artificial Intelligence and the 17th Innovative Applications of Artificial Intelligence Conference, AAAI-05/IAAI-05 - Pittsburgh, PA, United States Duration: Jul 9 2005 → Jul 13 2005

Other

Other	20th National Conference on Artificial Intelligence and the 17th Innovative Applications of Artificial Intelligence Conference, AAAI-05/IAAI-05
Country/Territory	United States
City	Pittsburgh, PA
Period	7/9/05 → 7/13/05

ASJC Scopus subject areas

Software
Artificial Intelligence

Library availability

Discover UIUC Full Text

Cite this

An inference model for semantic entailment in natural language. / De Salvo Braz, Rodrigo; Girju, Corina R; Punyakanok, Vasin et al.
2005. 1043-1049 Paper presented at 20th National Conference on Artificial Intelligence and the 17th Innovative Applications of Artificial Intelligence Conference, AAAI-05/IAAI-05, Pittsburgh, PA, United States.

Research output: Contribution to conference › Paper › peer-review

@conference{9107dd9df53b474a945cc1dbeec009e7,

title = "An inference model for semantic entailment in natural language",

abstract = "Semantic entailment is the problem of determining if the meaning of a given sentence entails that of another. This is a fundamental problem in natural language understanding that provides a broad framework for studying language variability and has a large number of applications. This paper presents a principled approach to this problem that builds on inducing representations of text snippets into a hierarchical knowledge representation along with a sound optimization-based inferential mechanism that makes use of it to decide semantic entailment. A preliminary evaluation on the PASCAL text collection is presented.",

author = "{De Salvo Braz}, Rodrigo and Girju, {Corina R} and Vasin Punyakanok and Dan Roth and Mark Sammons",

year = "2005",

language = "English (US)",

pages = "1043--1049",

note = "20th National Conference on Artificial Intelligence and the 17th Innovative Applications of Artificial Intelligence Conference, AAAI-05/IAAI-05 ; Conference date: 09-07-2005 Through 13-07-2005",

}

TY - CONF

T1 - An inference model for semantic entailment in natural language

AU - De Salvo Braz, Rodrigo

AU - Girju, Corina R

AU - Punyakanok, Vasin

AU - Roth, Dan

AU - Sammons, Mark

PY - 2005

Y1 - 2005

N2 - Semantic entailment is the problem of determining if the meaning of a given sentence entails that of another. This is a fundamental problem in natural language understanding that provides a broad framework for studying language variability and has a large number of applications. This paper presents a principled approach to this problem that builds on inducing representations of text snippets into a hierarchical knowledge representation along with a sound optimization-based inferential mechanism that makes use of it to decide semantic entailment. A preliminary evaluation on the PASCAL text collection is presented.

AB - Semantic entailment is the problem of determining if the meaning of a given sentence entails that of another. This is a fundamental problem in natural language understanding that provides a broad framework for studying language variability and has a large number of applications. This paper presents a principled approach to this problem that builds on inducing representations of text snippets into a hierarchical knowledge representation along with a sound optimization-based inferential mechanism that makes use of it to decide semantic entailment. A preliminary evaluation on the PASCAL text collection is presented.

UR - http://www.scopus.com/inward/record.url?scp=29344461064&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=29344461064&partnerID=8YFLogxK

M3 - Paper

AN - SCOPUS:29344461064

SP - 1043

EP - 1049

T2 - 20th National Conference on Artificial Intelligence and the 17th Innovative Applications of Artificial Intelligence Conference, AAAI-05/IAAI-05

Y2 - 9 July 2005 through 13 July 2005

ER -

An inference model for semantic entailment in natural language

Abstract

Other

ASJC Scopus subject areas

Library availability

Related links

Fingerprint

Cite this