Semi-supervised learning for automatic conceptual property extraction

Colin Kelly; Barry Devereux; Anna Korhonen

Semi-supervised learning for automatic conceptual property extraction

Colin Kelly, Barry Devereux, Anna Korhonen

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution

Abstract

For a given concrete noun concept, humans are usually able to cite properties (e.g., elephant is animal, car has wheels) of that concept; cognitive psychologists have theorised that such properties are fundamental to understanding the abstract mental representation of concepts in the brain. Consequently, the ability to automatically extract such properties would be of enormous benefit to the field of experimental psychology. This paper investigates the use of semi-supervised learning and support vector machines to automatically extract concept-relation-feature triples from two large corpora (Wikipedia and UKWAC) for concrete noun concepts. Previous approaches have relied on manually-generated rules and hand-crafted resources such as WordNet; our method requires neither yet achieves better performance than these prior approaches, measured both by comparison with a property norm-derived gold standard as well as direct human evaluation. Our technique performs particularly well on extracting features relevant to a given concept, and suggests a number of promising areas for future focus.

Original language	English
Title of host publication	Proceedings of the 2012 Workshop on Cognitive Modeling and Computational Linguistics, CMCL 2012 at the 2012 Conference of the North American Chapter of the Association for Computational Linguistics
Subtitle of host publication	Human Language Technologies, NAACL-HLT 2012
Editors	David Reitter, David Reitter, Roger Levy
Place of Publication	Stroudsburg, PA, USA
Publisher	Association for Computational Linguistics
Pages	11-20
Number of pages	10
ISBN (Electronic)	1937284204, 9781937284206
Publication status	Published - 2012
Externally published	Yes
Event	3rd Workshop on Cognitive Modeling and Computational Linguistics, CMCL 2012 at the 2012 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, NAACL-HLT 2012 - Montreal, Canada Duration: 07 Jun 2012 → …

Publication series

Name	Proceedings of the Annual Meeting of the Association for Computational Linguistics
Volume	2012-June
ISSN (Print)	0736-587X

Conference

Conference	3rd Workshop on Cognitive Modeling and Computational Linguistics, CMCL 2012 at the 2012 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, NAACL-HLT 2012
Country/Territory	Canada
City	Montreal
Period	07/06/2012 → …

Bibliographical note

Funding Information:
This research was supported by EPSRC grant EP/F030061/1. We are grateful to McRae and colleagues for making their norms publicly available, and to the anonymous reviewers for their helpful input.

Publisher Copyright:
© 2012 Association for Computational Linguistics

ASJC Scopus subject areas

Computer Science Applications
Linguistics and Language
Language and Linguistics

Access to Document

http://dl.acm.org/citation.cfm?id=2390304.2390307

Cite this

Kelly, C., Devereux, B., & Korhonen, A. (2012). Semi-supervised learning for automatic conceptual property extraction. In D. Reitter, D. Reitter, & R. Levy (Eds.), Proceedings of the 2012 Workshop on Cognitive Modeling and Computational Linguistics, CMCL 2012 at the 2012 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, NAACL-HLT 2012 (pp. 11-20). (Proceedings of the Annual Meeting of the Association for Computational Linguistics; Vol. 2012-June). Association for Computational Linguistics. http://dl.acm.org/citation.cfm?id=2390304.2390307

Kelly, Colin ; Devereux, Barry ; Korhonen, Anna. / Semi-supervised learning for automatic conceptual property extraction. Proceedings of the 2012 Workshop on Cognitive Modeling and Computational Linguistics, CMCL 2012 at the 2012 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, NAACL-HLT 2012. editor / David Reitter ; David Reitter ; Roger Levy. Stroudsburg, PA, USA : Association for Computational Linguistics, 2012. pp. 11-20 (Proceedings of the Annual Meeting of the Association for Computational Linguistics).

@inproceedings{4689e7010a8745179c309f7c89db1757,

title = "Semi-supervised learning for automatic conceptual property extraction",

abstract = "For a given concrete noun concept, humans are usually able to cite properties (e.g., elephant is animal, car has wheels) of that concept; cognitive psychologists have theorised that such properties are fundamental to understanding the abstract mental representation of concepts in the brain. Consequently, the ability to automatically extract such properties would be of enormous benefit to the field of experimental psychology. This paper investigates the use of semi-supervised learning and support vector machines to automatically extract concept-relation-feature triples from two large corpora (Wikipedia and UKWAC) for concrete noun concepts. Previous approaches have relied on manually-generated rules and hand-crafted resources such as WordNet; our method requires neither yet achieves better performance than these prior approaches, measured both by comparison with a property norm-derived gold standard as well as direct human evaluation. Our technique performs particularly well on extracting features relevant to a given concept, and suggests a number of promising areas for future focus.",

author = "Colin Kelly and Barry Devereux and Anna Korhonen",

note = "Funding Information: This research was supported by EPSRC grant EP/F030061/1. We are grateful to McRae and colleagues for making their norms publicly available, and to the anonymous reviewers for their helpful input. Publisher Copyright: {\textcopyright} 2012 Association for Computational Linguistics; 3rd Workshop on Cognitive Modeling and Computational Linguistics, CMCL 2012 at the 2012 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, NAACL-HLT 2012 ; Conference date: 07-06-2012",

year = "2012",

language = "English",

series = "Proceedings of the Annual Meeting of the Association for Computational Linguistics",

publisher = "Association for Computational Linguistics",

pages = "11--20",

editor = "David Reitter and David Reitter and Roger Levy",

booktitle = "Proceedings of the 2012 Workshop on Cognitive Modeling and Computational Linguistics, CMCL 2012 at the 2012 Conference of the North American Chapter of the Association for Computational Linguistics",

}

Kelly, C, Devereux, B & Korhonen, A 2012, Semi-supervised learning for automatic conceptual property extraction. in D Reitter, D Reitter & R Levy (eds), Proceedings of the 2012 Workshop on Cognitive Modeling and Computational Linguistics, CMCL 2012 at the 2012 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, NAACL-HLT 2012. Proceedings of the Annual Meeting of the Association for Computational Linguistics, vol. 2012-June, Association for Computational Linguistics, Stroudsburg, PA, USA, pp. 11-20, 3rd Workshop on Cognitive Modeling and Computational Linguistics, CMCL 2012 at the 2012 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, NAACL-HLT 2012, Montreal, Canada, 07/06/2012. <http://dl.acm.org/citation.cfm?id=2390304.2390307>

Semi-supervised learning for automatic conceptual property extraction. / Kelly, Colin; Devereux, Barry; Korhonen, Anna.
Proceedings of the 2012 Workshop on Cognitive Modeling and Computational Linguistics, CMCL 2012 at the 2012 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, NAACL-HLT 2012. ed. / David Reitter; David Reitter; Roger Levy. Stroudsburg, PA, USA: Association for Computational Linguistics, 2012. p. 11-20 (Proceedings of the Annual Meeting of the Association for Computational Linguistics; Vol. 2012-June).

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution

TY - GEN

T1 - Semi-supervised learning for automatic conceptual property extraction

AU - Kelly, Colin

AU - Devereux, Barry

AU - Korhonen, Anna

N1 - Funding Information: This research was supported by EPSRC grant EP/F030061/1. We are grateful to McRae and colleagues for making their norms publicly available, and to the anonymous reviewers for their helpful input. Publisher Copyright: © 2012 Association for Computational Linguistics

PY - 2012

Y1 - 2012

N2 - For a given concrete noun concept, humans are usually able to cite properties (e.g., elephant is animal, car has wheels) of that concept; cognitive psychologists have theorised that such properties are fundamental to understanding the abstract mental representation of concepts in the brain. Consequently, the ability to automatically extract such properties would be of enormous benefit to the field of experimental psychology. This paper investigates the use of semi-supervised learning and support vector machines to automatically extract concept-relation-feature triples from two large corpora (Wikipedia and UKWAC) for concrete noun concepts. Previous approaches have relied on manually-generated rules and hand-crafted resources such as WordNet; our method requires neither yet achieves better performance than these prior approaches, measured both by comparison with a property norm-derived gold standard as well as direct human evaluation. Our technique performs particularly well on extracting features relevant to a given concept, and suggests a number of promising areas for future focus.

AB - For a given concrete noun concept, humans are usually able to cite properties (e.g., elephant is animal, car has wheels) of that concept; cognitive psychologists have theorised that such properties are fundamental to understanding the abstract mental representation of concepts in the brain. Consequently, the ability to automatically extract such properties would be of enormous benefit to the field of experimental psychology. This paper investigates the use of semi-supervised learning and support vector machines to automatically extract concept-relation-feature triples from two large corpora (Wikipedia and UKWAC) for concrete noun concepts. Previous approaches have relied on manually-generated rules and hand-crafted resources such as WordNet; our method requires neither yet achieves better performance than these prior approaches, measured both by comparison with a property norm-derived gold standard as well as direct human evaluation. Our technique performs particularly well on extracting features relevant to a given concept, and suggests a number of promising areas for future focus.

UR - http://www.scopus.com/inward/record.url?scp=84906931444&partnerID=8YFLogxK

M3 - Conference contribution

T3 - Proceedings of the Annual Meeting of the Association for Computational Linguistics

SP - 11

EP - 20

BT - Proceedings of the 2012 Workshop on Cognitive Modeling and Computational Linguistics, CMCL 2012 at the 2012 Conference of the North American Chapter of the Association for Computational Linguistics

A2 - Reitter, David

A2 - Levy, Roger

PB - Association for Computational Linguistics

CY - Stroudsburg, PA, USA

T2 - 3rd Workshop on Cognitive Modeling and Computational Linguistics, CMCL 2012 at the 2012 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, NAACL-HLT 2012

Y2 - 7 June 2012

ER -

Kelly C, Devereux B, Korhonen A. Semi-supervised learning for automatic conceptual property extraction. In Reitter D, Reitter D, Levy R, editors, Proceedings of the 2012 Workshop on Cognitive Modeling and Computational Linguistics, CMCL 2012 at the 2012 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, NAACL-HLT 2012. Stroudsburg, PA, USA: Association for Computational Linguistics. 2012. p. 11-20. (Proceedings of the Annual Meeting of the Association for Computational Linguistics).

Semi-supervised learning for automatic conceptual property extraction

Abstract

Publication series

Conference

Bibliographical note

ASJC Scopus subject areas

Access to Document

Other files and links

Fingerprint

Cite this