Generalizing over lexical features

Selectional preferences for semantic role classification

Beñat Zapirain, Eneko Agirre, Lluis Marques

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

18 Citations (Scopus)

Abstract

This paper explores methods to alleviate the effect of lexical sparseness in the classification of verbal arguments. We show how automatically generated selectional preferences are able to generalize and perform better than lexical features in a large dataset for semantic role classification. The best results are obtained with a novel second-order distributional similarity measure, and the positive effect is specially relevant for out-of-domain data. Our findings suggest that selectional preferences have potential for improving a full system for Semantic Role Labeling.

Original languageEnglish
Title of host publicationACL-IJCNLP 2009 - Joint Conf. of the 47th Annual Meeting of the Association for Computational Linguistics and 4th Int. Joint Conf. on Natural Language Processing of the AFNLP, Proceedings of the Conf.
Pages73-76
Number of pages4
Publication statusPublished - 1 Dec 2009
Externally publishedYes
EventJoint Conference of the 47th Annual Meeting of the Association for Computational Linguistics and 4th International Joint Conference on Natural Language Processing of the AFNLP, ACL-IJCNLP 2009 - Suntec, Singapore
Duration: 2 Aug 20097 Aug 2009

Other

OtherJoint Conference of the 47th Annual Meeting of the Association for Computational Linguistics and 4th International Joint Conference on Natural Language Processing of the AFNLP, ACL-IJCNLP 2009
CountrySingapore
CitySuntec
Period2/8/097/8/09

Fingerprint

semantics
Semantic Roles
Labeling
Verbal Arguments

ASJC Scopus subject areas

  • Language and Linguistics
  • Linguistics and Language

Cite this

Zapirain, B., Agirre, E., & Marques, L. (2009). Generalizing over lexical features: Selectional preferences for semantic role classification. In ACL-IJCNLP 2009 - Joint Conf. of the 47th Annual Meeting of the Association for Computational Linguistics and 4th Int. Joint Conf. on Natural Language Processing of the AFNLP, Proceedings of the Conf. (pp. 73-76)

Generalizing over lexical features : Selectional preferences for semantic role classification. / Zapirain, Beñat; Agirre, Eneko; Marques, Lluis.

ACL-IJCNLP 2009 - Joint Conf. of the 47th Annual Meeting of the Association for Computational Linguistics and 4th Int. Joint Conf. on Natural Language Processing of the AFNLP, Proceedings of the Conf.. 2009. p. 73-76.

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

Zapirain, B, Agirre, E & Marques, L 2009, Generalizing over lexical features: Selectional preferences for semantic role classification. in ACL-IJCNLP 2009 - Joint Conf. of the 47th Annual Meeting of the Association for Computational Linguistics and 4th Int. Joint Conf. on Natural Language Processing of the AFNLP, Proceedings of the Conf.. pp. 73-76, Joint Conference of the 47th Annual Meeting of the Association for Computational Linguistics and 4th International Joint Conference on Natural Language Processing of the AFNLP, ACL-IJCNLP 2009, Suntec, Singapore, 2/8/09.
Zapirain B, Agirre E, Marques L. Generalizing over lexical features: Selectional preferences for semantic role classification. In ACL-IJCNLP 2009 - Joint Conf. of the 47th Annual Meeting of the Association for Computational Linguistics and 4th Int. Joint Conf. on Natural Language Processing of the AFNLP, Proceedings of the Conf.. 2009. p. 73-76
Zapirain, Beñat ; Agirre, Eneko ; Marques, Lluis. / Generalizing over lexical features : Selectional preferences for semantic role classification. ACL-IJCNLP 2009 - Joint Conf. of the 47th Annual Meeting of the Association for Computational Linguistics and 4th Int. Joint Conf. on Natural Language Processing of the AFNLP, Proceedings of the Conf.. 2009. pp. 73-76
@inproceedings{23a1e68f402d4eab947a83615f9010a3,
title = "Generalizing over lexical features: Selectional preferences for semantic role classification",
abstract = "This paper explores methods to alleviate the effect of lexical sparseness in the classification of verbal arguments. We show how automatically generated selectional preferences are able to generalize and perform better than lexical features in a large dataset for semantic role classification. The best results are obtained with a novel second-order distributional similarity measure, and the positive effect is specially relevant for out-of-domain data. Our findings suggest that selectional preferences have potential for improving a full system for Semantic Role Labeling.",
author = "Be{\~n}at Zapirain and Eneko Agirre and Lluis Marques",
year = "2009",
month = "12",
day = "1",
language = "English",
isbn = "9781617382581",
pages = "73--76",
booktitle = "ACL-IJCNLP 2009 - Joint Conf. of the 47th Annual Meeting of the Association for Computational Linguistics and 4th Int. Joint Conf. on Natural Language Processing of the AFNLP, Proceedings of the Conf.",

}

TY - GEN

T1 - Generalizing over lexical features

T2 - Selectional preferences for semantic role classification

AU - Zapirain, Beñat

AU - Agirre, Eneko

AU - Marques, Lluis

PY - 2009/12/1

Y1 - 2009/12/1

N2 - This paper explores methods to alleviate the effect of lexical sparseness in the classification of verbal arguments. We show how automatically generated selectional preferences are able to generalize and perform better than lexical features in a large dataset for semantic role classification. The best results are obtained with a novel second-order distributional similarity measure, and the positive effect is specially relevant for out-of-domain data. Our findings suggest that selectional preferences have potential for improving a full system for Semantic Role Labeling.

AB - This paper explores methods to alleviate the effect of lexical sparseness in the classification of verbal arguments. We show how automatically generated selectional preferences are able to generalize and perform better than lexical features in a large dataset for semantic role classification. The best results are obtained with a novel second-order distributional similarity measure, and the positive effect is specially relevant for out-of-domain data. Our findings suggest that selectional preferences have potential for improving a full system for Semantic Role Labeling.

UR - http://www.scopus.com/inward/record.url?scp=79952565204&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=79952565204&partnerID=8YFLogxK

M3 - Conference contribution

SN - 9781617382581

SP - 73

EP - 76

BT - ACL-IJCNLP 2009 - Joint Conf. of the 47th Annual Meeting of the Association for Computational Linguistics and 4th Int. Joint Conf. on Natural Language Processing of the AFNLP, Proceedings of the Conf.

ER -