A Morphological Analyzer for Gulf Arabic Verbs

Salam Khalifa; Sara Hassan; Nizar Habash

doi:10.18653/v1/W17-1305

A Morphological Analyzer for Gulf Arabic Verbs

Salam Khalifa, Sara Hassan, Nizar Habash

Computer Science

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

Abstract

We present CALIMAGLF, a Gulf Arabic morphological analyzer currently covering over 2,600 verbal lemmas. We describe in detail the process of building the analyzer starting from phonetic dictionary entries to fully inflected orthographic paradigms and associated lexicon and orthographic variants. We evaluate the coverage of CALIMA-GLF against Modern Standard Arabic and Egyptian Arabic analyzers on part of a Gulf Arabic novel. CALIMA-GLF verb analysis token recall for identifying correct POS tag outperforms both the Modern Standard Arabic and Egyptian Arabic analyzers by over 27.4% and 16.9% absolute, respectively.

Original language	Undefined
Title of host publication	Proceedings of the Third Arabic Natural Language Processing Workshop
Place of Publication	Valencia, Spain
Publisher	Association for Computational Linguistics (ACL)
Pages	35-45
Number of pages	11
DOIs	https://doi.org/10.18653/v1/W17-1305
State	Published - Apr 1 2017

Access to Document

10.18653/v1/W17-1305

https://www.aclweb.org/anthology/W17-1305

Cite this

@inproceedings{eb0730222bbb44fe8139dac2ad0a5705,

title = "A Morphological Analyzer for Gulf Arabic Verbs",

abstract = "We present CALIMAGLF, a Gulf Arabic morphological analyzer currently covering over 2,600 verbal lemmas. We describe in detail the process of building the analyzer starting from phonetic dictionary entries to fully inflected orthographic paradigms and associated lexicon and orthographic variants. We evaluate the coverage of CALIMA-GLF against Modern Standard Arabic and Egyptian Arabic analyzers on part of a Gulf Arabic novel. CALIMA-GLF verb analysis token recall for identifying correct POS tag outperforms both the Modern Standard Arabic and Egyptian Arabic analyzers by over 27.4% and 16.9% absolute, respectively.",

author = "Salam Khalifa and Sara Hassan and Nizar Habash",

year = "2017",

month = apr,

day = "1",

doi = "10.18653/v1/W17-1305",

language = "Undefined",

pages = "35--45",

booktitle = "Proceedings of the Third Arabic Natural Language Processing Workshop",

publisher = "Association for Computational Linguistics (ACL)",

}

TY - GEN

T1 - A Morphological Analyzer for Gulf Arabic Verbs

AU - Khalifa, Salam

AU - Hassan, Sara

AU - Habash, Nizar

PY - 2017/4/1

Y1 - 2017/4/1

N2 - We present CALIMAGLF, a Gulf Arabic morphological analyzer currently covering over 2,600 verbal lemmas. We describe in detail the process of building the analyzer starting from phonetic dictionary entries to fully inflected orthographic paradigms and associated lexicon and orthographic variants. We evaluate the coverage of CALIMA-GLF against Modern Standard Arabic and Egyptian Arabic analyzers on part of a Gulf Arabic novel. CALIMA-GLF verb analysis token recall for identifying correct POS tag outperforms both the Modern Standard Arabic and Egyptian Arabic analyzers by over 27.4% and 16.9% absolute, respectively.

AB - We present CALIMAGLF, a Gulf Arabic morphological analyzer currently covering over 2,600 verbal lemmas. We describe in detail the process of building the analyzer starting from phonetic dictionary entries to fully inflected orthographic paradigms and associated lexicon and orthographic variants. We evaluate the coverage of CALIMA-GLF against Modern Standard Arabic and Egyptian Arabic analyzers on part of a Gulf Arabic novel. CALIMA-GLF verb analysis token recall for identifying correct POS tag outperforms both the Modern Standard Arabic and Egyptian Arabic analyzers by over 27.4% and 16.9% absolute, respectively.

U2 - 10.18653/v1/W17-1305

DO - 10.18653/v1/W17-1305

M3 - Conference contribution

SP - 35

EP - 45

BT - Proceedings of the Third Arabic Natural Language Processing Workshop

PB - Association for Computational Linguistics (ACL)

CY - Valencia, Spain

ER -