Semantic role labeling via FrameNet, VerbNet and PropBank

Ana Maria Giuglea, Alessandro Moschitti

Research output: Chapter in Book/Report/Conference proceedingConference contribution

48 Citations (Scopus)

Abstract

This article describes a robust semantic parser that uses a broad knowledge base created by interconnecting three major resources: FrameNet, VerbNet and PropBank. The FrameNet corpus contains the examples annotated with semantic roles whereas the VerbNet lexicon provides the knowledge about the syntactic behavior of the verbs. We connect VerbNet and FrameNet by mapping the FrameNet frames to the VerbNet Intersective Levin classes. The PropBank corpus, which is tightly connected to the VerbNet lexicon, is used to increase the verb coverage and also to test the effectiveness of our approach. The results indicate that our model is an interesting step towards the design of more robust semantic parsers.

Original languageEnglish
Title of host publicationCOLING/ACL 2006 - 21st International Conference on Computational Linguistics and 44th Annual Meeting of the Association for Computational Linguistics, Proceedings of the Conference
Pages929-936
Number of pages8
Volume1
Publication statusPublished - 1 Dec 2006
Externally publishedYes
Event21st International Conference on Computational Linguistics and 44th Annual Meeting of the Association for Computational Linguistics, COLING/ACL 2006 - Sydney, NSW, Australia
Duration: 17 Jul 200621 Jul 2006

Other

Other21st International Conference on Computational Linguistics and 44th Annual Meeting of the Association for Computational Linguistics, COLING/ACL 2006
CountryAustralia
CitySydney, NSW
Period17/7/0621/7/06

Fingerprint

semantics
coverage
resources
Semantic Roles
Verbs
Labeling
Lexicon
Parsers
Syntax
Resources

ASJC Scopus subject areas

  • Language and Linguistics
  • Linguistics and Language

Cite this

Giuglea, A. M., & Moschitti, A. (2006). Semantic role labeling via FrameNet, VerbNet and PropBank. In COLING/ACL 2006 - 21st International Conference on Computational Linguistics and 44th Annual Meeting of the Association for Computational Linguistics, Proceedings of the Conference (Vol. 1, pp. 929-936)

Semantic role labeling via FrameNet, VerbNet and PropBank. / Giuglea, Ana Maria; Moschitti, Alessandro.

COLING/ACL 2006 - 21st International Conference on Computational Linguistics and 44th Annual Meeting of the Association for Computational Linguistics, Proceedings of the Conference. Vol. 1 2006. p. 929-936.

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Giuglea, AM & Moschitti, A 2006, Semantic role labeling via FrameNet, VerbNet and PropBank. in COLING/ACL 2006 - 21st International Conference on Computational Linguistics and 44th Annual Meeting of the Association for Computational Linguistics, Proceedings of the Conference. vol. 1, pp. 929-936, 21st International Conference on Computational Linguistics and 44th Annual Meeting of the Association for Computational Linguistics, COLING/ACL 2006, Sydney, NSW, Australia, 17/7/06.
Giuglea AM, Moschitti A. Semantic role labeling via FrameNet, VerbNet and PropBank. In COLING/ACL 2006 - 21st International Conference on Computational Linguistics and 44th Annual Meeting of the Association for Computational Linguistics, Proceedings of the Conference. Vol. 1. 2006. p. 929-936
Giuglea, Ana Maria ; Moschitti, Alessandro. / Semantic role labeling via FrameNet, VerbNet and PropBank. COLING/ACL 2006 - 21st International Conference on Computational Linguistics and 44th Annual Meeting of the Association for Computational Linguistics, Proceedings of the Conference. Vol. 1 2006. pp. 929-936
@inproceedings{89bebc49209d4065b4ed7eb938b918b9,
title = "Semantic role labeling via FrameNet, VerbNet and PropBank",
abstract = "This article describes a robust semantic parser that uses a broad knowledge base created by interconnecting three major resources: FrameNet, VerbNet and PropBank. The FrameNet corpus contains the examples annotated with semantic roles whereas the VerbNet lexicon provides the knowledge about the syntactic behavior of the verbs. We connect VerbNet and FrameNet by mapping the FrameNet frames to the VerbNet Intersective Levin classes. The PropBank corpus, which is tightly connected to the VerbNet lexicon, is used to increase the verb coverage and also to test the effectiveness of our approach. The results indicate that our model is an interesting step towards the design of more robust semantic parsers.",
author = "Giuglea, {Ana Maria} and Alessandro Moschitti",
year = "2006",
month = "12",
day = "1",
language = "English",
isbn = "1932432655",
volume = "1",
pages = "929--936",
booktitle = "COLING/ACL 2006 - 21st International Conference on Computational Linguistics and 44th Annual Meeting of the Association for Computational Linguistics, Proceedings of the Conference",

}

TY - GEN

T1 - Semantic role labeling via FrameNet, VerbNet and PropBank

AU - Giuglea, Ana Maria

AU - Moschitti, Alessandro

PY - 2006/12/1

Y1 - 2006/12/1

N2 - This article describes a robust semantic parser that uses a broad knowledge base created by interconnecting three major resources: FrameNet, VerbNet and PropBank. The FrameNet corpus contains the examples annotated with semantic roles whereas the VerbNet lexicon provides the knowledge about the syntactic behavior of the verbs. We connect VerbNet and FrameNet by mapping the FrameNet frames to the VerbNet Intersective Levin classes. The PropBank corpus, which is tightly connected to the VerbNet lexicon, is used to increase the verb coverage and also to test the effectiveness of our approach. The results indicate that our model is an interesting step towards the design of more robust semantic parsers.

AB - This article describes a robust semantic parser that uses a broad knowledge base created by interconnecting three major resources: FrameNet, VerbNet and PropBank. The FrameNet corpus contains the examples annotated with semantic roles whereas the VerbNet lexicon provides the knowledge about the syntactic behavior of the verbs. We connect VerbNet and FrameNet by mapping the FrameNet frames to the VerbNet Intersective Levin classes. The PropBank corpus, which is tightly connected to the VerbNet lexicon, is used to increase the verb coverage and also to test the effectiveness of our approach. The results indicate that our model is an interesting step towards the design of more robust semantic parsers.

UR - http://www.scopus.com/inward/record.url?scp=53049085297&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=53049085297&partnerID=8YFLogxK

M3 - Conference contribution

SN - 1932432655

SN - 9781932432657

VL - 1

SP - 929

EP - 936

BT - COLING/ACL 2006 - 21st International Conference on Computational Linguistics and 44th Annual Meeting of the Association for Computational Linguistics, Proceedings of the Conference

ER -