Learning semantic constraints for the automatic discovery of part-whole relations

Roxana Girju; Adriana Badulescu; Dan Moldovan

Learning semantic constraints for the automatic discovery of part-whole relations

Roxana Girju, Adriana Badulescu, Dan Moldovan

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

Abstract

The discovery of semantic relations from text becomes increasingly important for applications such as Question Answering, Information Extraction, Text Summarization, Text Understanding, and others. The semantic relations are detected by checking selectional constraints. This paper presents a method and its results for learning semantic constraints to detect part-whole relations. Twenty constraints were found. Their validity was tested on a 10,000 sentence corpus, and the targeted part-whole relations were detected with an accuracy of 83%.

Original language	English (US)
State	Published - 2003
Externally published	Yes
Event	2003 Human Language Technology Conference of the North American Chapter of the Association for Computational Linguistics, HLT-NAACL 2003 - Edmonton, Canada Duration: May 27 2003 → Jun 1 2003

Conference

Conference	2003 Human Language Technology Conference of the North American Chapter of the Association for Computational Linguistics, HLT-NAACL 2003
Country/Territory	Canada
City	Edmonton
Period	5/27/03 → 6/1/03

ASJC Scopus subject areas

Language and Linguistics
Linguistics and Language

Library availability

Discover UIUC Full Text

Cite this

Learning semantic constraints for the automatic discovery of part-whole relations. / Girju, Roxana; Badulescu, Adriana; Moldovan, Dan.
2003. Paper presented at 2003 Human Language Technology Conference of the North American Chapter of the Association for Computational Linguistics, HLT-NAACL 2003, Edmonton, Canada.

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

@conference{74b98a828efd4ef2b146b86e19a75192,

title = "Learning semantic constraints for the automatic discovery of part-whole relations",

abstract = "The discovery of semantic relations from text becomes increasingly important for applications such as Question Answering, Information Extraction, Text Summarization, Text Understanding, and others. The semantic relations are detected by checking selectional constraints. This paper presents a method and its results for learning semantic constraints to detect part-whole relations. Twenty constraints were found. Their validity was tested on a 10,000 sentence corpus, and the targeted part-whole relations were detected with an accuracy of 83%.",

author = "Roxana Girju and Adriana Badulescu and Dan Moldovan",

note = "Publisher Copyright: {\textcopyright} 2003 Proceedings of the 2003 Human Language Technology Conference of the North American Chapter of the Association for Computational Linguistics, HLT-NAACL 2003. All rights reserved.; 2003 Human Language Technology Conference of the North American Chapter of the Association for Computational Linguistics, HLT-NAACL 2003 ; Conference date: 27-05-2003 Through 01-06-2003",

year = "2003",

language = "English (US)",

}

TY - CONF

T1 - Learning semantic constraints for the automatic discovery of part-whole relations

AU - Girju, Roxana

AU - Badulescu, Adriana

AU - Moldovan, Dan

N1 - Publisher Copyright: © 2003 Proceedings of the 2003 Human Language Technology Conference of the North American Chapter of the Association for Computational Linguistics, HLT-NAACL 2003. All rights reserved.

PY - 2003

Y1 - 2003

N2 - The discovery of semantic relations from text becomes increasingly important for applications such as Question Answering, Information Extraction, Text Summarization, Text Understanding, and others. The semantic relations are detected by checking selectional constraints. This paper presents a method and its results for learning semantic constraints to detect part-whole relations. Twenty constraints were found. Their validity was tested on a 10,000 sentence corpus, and the targeted part-whole relations were detected with an accuracy of 83%.

AB - The discovery of semantic relations from text becomes increasingly important for applications such as Question Answering, Information Extraction, Text Summarization, Text Understanding, and others. The semantic relations are detected by checking selectional constraints. This paper presents a method and its results for learning semantic constraints to detect part-whole relations. Twenty constraints were found. Their validity was tested on a 10,000 sentence corpus, and the targeted part-whole relations were detected with an accuracy of 83%.

UR - http://www.scopus.com/inward/record.url?scp=85118719409&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85118719409&partnerID=8YFLogxK

M3 - Paper

AN - SCOPUS:85118719409

T2 - 2003 Human Language Technology Conference of the North American Chapter of the Association for Computational Linguistics, HLT-NAACL 2003

Y2 - 27 May 2003 through 1 June 2003

ER -

Learning semantic constraints for the automatic discovery of part-whole relations

Abstract

Conference

ASJC Scopus subject areas

Library availability

Related links

Fingerprint

Cite this