Semantic parsing of modern standard Arabic

Mona T. Diab, Alessandro Moschitti

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

2 Citations (Scopus)

Abstract

Shallow approaches to text processing have been garnering a lot of attention recently. Specifically, shallow approaches to semantic processing are making large strides in the direction of efficiently and effectively deriving tacit semantic information from text. Semantic Role Labeling (SRL) is one such approach. SRL is the task by which arguments of a predicate are identified and classified. In this paper, we present a system for Arabic SRL. To our knowledge, this is the first system to address the problem of semantic parsing of Arabic. Our SRL system is an SVM based system using polynomial kernels. The system is evaluated on the released SEMEVAL 2007 development and test data. Given the size of the training data, the obtained results are very promising. The Arabic SRL system yields an Fβ=1 score of 94.06% on argument boundary detection and an overall Fβ=1 score of 81.43% on the complete semantic role labeling task using test data.

Original languageEnglish
Title of host publicationInternational Conference Recent Advances in Natural Language Processing, RANLP
PublisherAssociation for Computational Linguistics (ACL)
Pages162-166
Number of pages5
Volume2007-January
ISBN (Print)9789549174373
Publication statusPublished - 2007
Externally publishedYes
EventInternational Conference Recent Advances in Natural Language Processing, RANLP 2007 - Borovets, Bulgaria
Duration: 27 Sep 200729 Sep 2007

Other

OtherInternational Conference Recent Advances in Natural Language Processing, RANLP 2007
CountryBulgaria
CityBorovets
Period27/9/0729/9/07

Fingerprint

Semantics
Labeling
Text processing
Polynomials
Processing

Keywords

  • Arabic language
  • Semantic Role Labeling

ASJC Scopus subject areas

  • Artificial Intelligence
  • Computer Science Applications
  • Software
  • Electrical and Electronic Engineering

Cite this

Diab, M. T., & Moschitti, A. (2007). Semantic parsing of modern standard Arabic. In International Conference Recent Advances in Natural Language Processing, RANLP (Vol. 2007-January, pp. 162-166). Association for Computational Linguistics (ACL).

Semantic parsing of modern standard Arabic. / Diab, Mona T.; Moschitti, Alessandro.

International Conference Recent Advances in Natural Language Processing, RANLP. Vol. 2007-January Association for Computational Linguistics (ACL), 2007. p. 162-166.

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

Diab, MT & Moschitti, A 2007, Semantic parsing of modern standard Arabic. in International Conference Recent Advances in Natural Language Processing, RANLP. vol. 2007-January, Association for Computational Linguistics (ACL), pp. 162-166, International Conference Recent Advances in Natural Language Processing, RANLP 2007, Borovets, Bulgaria, 27/9/07.
Diab MT, Moschitti A. Semantic parsing of modern standard Arabic. In International Conference Recent Advances in Natural Language Processing, RANLP. Vol. 2007-January. Association for Computational Linguistics (ACL). 2007. p. 162-166
Diab, Mona T. ; Moschitti, Alessandro. / Semantic parsing of modern standard Arabic. International Conference Recent Advances in Natural Language Processing, RANLP. Vol. 2007-January Association for Computational Linguistics (ACL), 2007. pp. 162-166
@inproceedings{66958d4955014db5851314e90310ea61,
title = "Semantic parsing of modern standard Arabic",
abstract = "Shallow approaches to text processing have been garnering a lot of attention recently. Specifically, shallow approaches to semantic processing are making large strides in the direction of efficiently and effectively deriving tacit semantic information from text. Semantic Role Labeling (SRL) is one such approach. SRL is the task by which arguments of a predicate are identified and classified. In this paper, we present a system for Arabic SRL. To our knowledge, this is the first system to address the problem of semantic parsing of Arabic. Our SRL system is an SVM based system using polynomial kernels. The system is evaluated on the released SEMEVAL 2007 development and test data. Given the size of the training data, the obtained results are very promising. The Arabic SRL system yields an Fβ=1 score of 94.06{\%} on argument boundary detection and an overall Fβ=1 score of 81.43{\%} on the complete semantic role labeling task using test data.",
keywords = "Arabic language, Semantic Role Labeling",
author = "Diab, {Mona T.} and Alessandro Moschitti",
year = "2007",
language = "English",
isbn = "9789549174373",
volume = "2007-January",
pages = "162--166",
booktitle = "International Conference Recent Advances in Natural Language Processing, RANLP",
publisher = "Association for Computational Linguistics (ACL)",

}

TY - GEN

T1 - Semantic parsing of modern standard Arabic

AU - Diab, Mona T.

AU - Moschitti, Alessandro

PY - 2007

Y1 - 2007

N2 - Shallow approaches to text processing have been garnering a lot of attention recently. Specifically, shallow approaches to semantic processing are making large strides in the direction of efficiently and effectively deriving tacit semantic information from text. Semantic Role Labeling (SRL) is one such approach. SRL is the task by which arguments of a predicate are identified and classified. In this paper, we present a system for Arabic SRL. To our knowledge, this is the first system to address the problem of semantic parsing of Arabic. Our SRL system is an SVM based system using polynomial kernels. The system is evaluated on the released SEMEVAL 2007 development and test data. Given the size of the training data, the obtained results are very promising. The Arabic SRL system yields an Fβ=1 score of 94.06% on argument boundary detection and an overall Fβ=1 score of 81.43% on the complete semantic role labeling task using test data.

AB - Shallow approaches to text processing have been garnering a lot of attention recently. Specifically, shallow approaches to semantic processing are making large strides in the direction of efficiently and effectively deriving tacit semantic information from text. Semantic Role Labeling (SRL) is one such approach. SRL is the task by which arguments of a predicate are identified and classified. In this paper, we present a system for Arabic SRL. To our knowledge, this is the first system to address the problem of semantic parsing of Arabic. Our SRL system is an SVM based system using polynomial kernels. The system is evaluated on the released SEMEVAL 2007 development and test data. Given the size of the training data, the obtained results are very promising. The Arabic SRL system yields an Fβ=1 score of 94.06% on argument boundary detection and an overall Fβ=1 score of 81.43% on the complete semantic role labeling task using test data.

KW - Arabic language

KW - Semantic Role Labeling

UR - http://www.scopus.com/inward/record.url?scp=84959042090&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84959042090&partnerID=8YFLogxK

M3 - Conference contribution

AN - SCOPUS:84959042090

SN - 9789549174373

VL - 2007-January

SP - 162

EP - 166

BT - International Conference Recent Advances in Natural Language Processing, RANLP

PB - Association for Computational Linguistics (ACL)

ER -