Home > Research > Publications & Outputs > Towards a Better Semantic Role Labeling of Comp...

Research

Links

Text available via DOI:

View graph of relations

Towards a Better Semantic Role Labeling of Complex Predicates

Research output: Contribution in Book/Report/Proceedings - With ISBN/ISSN › Conference contribution/Paper › peer-review

Published

Standard

Towards a Better Semantic Role Labeling of Complex Predicates. / Jagfeld, Glorianna; van der Plas, Lonneke.
Proceedings of the 2015 Conference of the North American Chapter of the Association for Computational Linguistics: Student Research Workshop. Association for Computational Linguistics, 2015. p. 33-39.

Research output: Contribution in Book/Report/Proceedings - With ISBN/ISSN › Conference contribution/Paper › peer-review

Harvard

Jagfeld, G & van der Plas, L 2015, Towards a Better Semantic Role Labeling of Complex Predicates. in Proceedings of the 2015 Conference of the North American Chapter of the Association for Computational Linguistics: Student Research Workshop. Association for Computational Linguistics, pp. 33-39, NAACL 2015 Student Research Workshop, Denver, Colorado, United States, 1/06/15. https://doi.org/10.3115/v1/N15-2005

APA

Jagfeld, G., & van der Plas, L. (2015). Towards a Better Semantic Role Labeling of Complex Predicates. In Proceedings of the 2015 Conference of the North American Chapter of the Association for Computational Linguistics: Student Research Workshop (pp. 33-39). Association for Computational Linguistics. https://doi.org/10.3115/v1/N15-2005

Vancouver

Jagfeld G, van der Plas L. Towards a Better Semantic Role Labeling of Complex Predicates. In Proceedings of the 2015 Conference of the North American Chapter of the Association for Computational Linguistics: Student Research Workshop. Association for Computational Linguistics. 2015. p. 33-39 doi: 10.3115/v1/N15-2005

Author

Jagfeld, Glorianna ; van der Plas, Lonneke. / Towards a Better Semantic Role Labeling of Complex Predicates. Proceedings of the 2015 Conference of the North American Chapter of the Association for Computational Linguistics: Student Research Workshop. Association for Computational Linguistics, 2015. pp. 33-39

Bibtex

@inproceedings{0534ae4db0f14728892a47435f0e39ae,
title = "Towards a Better Semantic Role Labeling of Complex Predicates",
abstract = "We propose a way to automatically improve the annotation of verbal complex predicates in PropBank which until now has been treating language mostly in a compositional manner. In order to minimize the manual re-annotation effort, we build on the recently introduced concept of aliasing complex predicates to existing PropBank rolesets which encompass the same meaning and argument structure. We suggest to find aliases automatically by applying a multilingual distributional model that uses the translations of simple and complex predicates as features. Furthermore, we set up an annotation effort to obtain a frequency balanced, realistic test set for this task. Our method reaches an accuracy of 44% on this test set and 72% for the more frequent test items in a lenient evaluation, which is not far from the upper bounds from human annotation.",
author = "Glorianna Jagfeld and {van der Plas}, Lonneke",
year = "2015",
month = may,
doi = "10.3115/v1/N15-2005",
language = "English",
pages = "33--39",
booktitle = "Proceedings of the 2015 Conference of the North American Chapter of the Association for Computational Linguistics: Student Research Workshop",
publisher = "Association for Computational Linguistics",
note = "NAACL 2015 Student Research Workshop, SRW ; Conference date: 01-06-2015",
url = "https://sites.google.com/site/naaclsrw2015/home",

}

RIS

TY - GEN

T1 - Towards a Better Semantic Role Labeling of Complex Predicates

AU - Jagfeld, Glorianna

AU - van der Plas, Lonneke

PY - 2015/5

Y1 - 2015/5

N2 - We propose a way to automatically improve the annotation of verbal complex predicates in PropBank which until now has been treating language mostly in a compositional manner. In order to minimize the manual re-annotation effort, we build on the recently introduced concept of aliasing complex predicates to existing PropBank rolesets which encompass the same meaning and argument structure. We suggest to find aliases automatically by applying a multilingual distributional model that uses the translations of simple and complex predicates as features. Furthermore, we set up an annotation effort to obtain a frequency balanced, realistic test set for this task. Our method reaches an accuracy of 44% on this test set and 72% for the more frequent test items in a lenient evaluation, which is not far from the upper bounds from human annotation.

AB - We propose a way to automatically improve the annotation of verbal complex predicates in PropBank which until now has been treating language mostly in a compositional manner. In order to minimize the manual re-annotation effort, we build on the recently introduced concept of aliasing complex predicates to existing PropBank rolesets which encompass the same meaning and argument structure. We suggest to find aliases automatically by applying a multilingual distributional model that uses the translations of simple and complex predicates as features. Furthermore, we set up an annotation effort to obtain a frequency balanced, realistic test set for this task. Our method reaches an accuracy of 44% on this test set and 72% for the more frequent test items in a lenient evaluation, which is not far from the upper bounds from human annotation.

U2 - 10.3115/v1/N15-2005

DO - 10.3115/v1/N15-2005

M3 - Conference contribution/Paper

SP - 33

EP - 39

BT - Proceedings of the 2015 Conference of the North American Chapter of the Association for Computational Linguistics: Student Research Workshop

PB - Association for Computational Linguistics

T2 - NAACL 2015 Student Research Workshop

Y2 - 1 June 2015

ER -