@inproceedings{alzaabi-etal-2026-gahwa,
title = "Gahwa: A Computational Lexicon for Emirati {A}rabic",
author = "Alzaabi, Saeed and
Khalifa, Salam and
Saeed, Mostafa and
Dibas, Shahd and
Aldarmaki, Hanan and
Habash, Nizar",
editor = "Abdul-Mageed, Muhammad and
Elsayed, Tamer and
Bouamor, Houda and
El-Beltagy, Samhaa and
Al-Khalifa, Hend and
Abdelali, Ahmed and
Elmadany, AbdelRahim and
El Mekki, Abdellah and
Darwish, Kareem and
Alkhereyf, Sakhar and
Luqman, Hamzah and
Khalifa, Salam and
Magdy, Samar and
Alyafeai, Zaid and
Hamed, Injy and
Zaghouani, Wajdi and
Zitouni, Imed",
booktitle = "Proceedings of The Fourth {A}rabic Natural Language Processing Conference",
month = oct,
year = "2026",
address = "Budapest, Hungary",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2026.arabicnlp-main.16/",
pages = "219--227",
ISBN = "979-8-89176-473-6",
abstract = "Emirati Arabic remains one of the least-resourced Arabic dialects, with lexical information scattered across corpora, morphological databases, and dictionaries developed under incompatible annotation schemes. We present Gahwa, a machine-readable lexicon constructed by extracting, enriching, and standardizing evidence from an annotated Emirati corpus, a Gulf Arabic verb database, and a Gulf Arabic Wiktionary, unifying their input into one lemma-POS keyed scheme. We evaluate Gahwa through automatic coverage analysis of three Emirati datasets, GumarAE, Mixat, and the Ramsa Corpus, against existing Arabic morphological resources, and through analysis of out-of-vocabulary (OOV) forms. Results show that Gahwa has high word coverage across the three datasets, achieving 89.1-94.2{\%} effective dediacritized lemma-POS token coverage, while the remaining OOV cases primarily reflect lexical gaps, orthographic variations, fused expressions, and morphological gaps."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="alzaabi-etal-2026-gahwa">
<titleInfo>
<title>Gahwa: A Computational Lexicon for Emirati Arabic</title>
</titleInfo>
<name type="personal">
<namePart type="given">Saeed</namePart>
<namePart type="family">Alzaabi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Salam</namePart>
<namePart type="family">Khalifa</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Mostafa</namePart>
<namePart type="family">Saeed</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Shahd</namePart>
<namePart type="family">Dibas</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Hanan</namePart>
<namePart type="family">Aldarmaki</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Nizar</namePart>
<namePart type="family">Habash</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2026-10</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of The Fourth Arabic Natural Language Processing Conference</title>
</titleInfo>
<name type="personal">
<namePart type="given">Muhammad</namePart>
<namePart type="family">Abdul-Mageed</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Tamer</namePart>
<namePart type="family">Elsayed</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Houda</namePart>
<namePart type="family">Bouamor</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Samhaa</namePart>
<namePart type="family">El-Beltagy</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Hend</namePart>
<namePart type="family">Al-Khalifa</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ahmed</namePart>
<namePart type="family">Abdelali</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">AbdelRahim</namePart>
<namePart type="family">Elmadany</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Abdellah</namePart>
<namePart type="family">El Mekki</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Kareem</namePart>
<namePart type="family">Darwish</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sakhar</namePart>
<namePart type="family">Alkhereyf</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Hamzah</namePart>
<namePart type="family">Luqman</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Salam</namePart>
<namePart type="family">Khalifa</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Samar</namePart>
<namePart type="family">Magdy</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Zaid</namePart>
<namePart type="family">Alyafeai</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Injy</namePart>
<namePart type="family">Hamed</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Wajdi</namePart>
<namePart type="family">Zaghouani</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Imed</namePart>
<namePart type="family">Zitouni</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Budapest, Hungary</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
<identifier type="isbn">979-8-89176-473-6</identifier>
</relatedItem>
<abstract>Emirati Arabic remains one of the least-resourced Arabic dialects, with lexical information scattered across corpora, morphological databases, and dictionaries developed under incompatible annotation schemes. We present Gahwa, a machine-readable lexicon constructed by extracting, enriching, and standardizing evidence from an annotated Emirati corpus, a Gulf Arabic verb database, and a Gulf Arabic Wiktionary, unifying their input into one lemma-POS keyed scheme. We evaluate Gahwa through automatic coverage analysis of three Emirati datasets, GumarAE, Mixat, and the Ramsa Corpus, against existing Arabic morphological resources, and through analysis of out-of-vocabulary (OOV) forms. Results show that Gahwa has high word coverage across the three datasets, achieving 89.1-94.2% effective dediacritized lemma-POS token coverage, while the remaining OOV cases primarily reflect lexical gaps, orthographic variations, fused expressions, and morphological gaps.</abstract>
<identifier type="citekey">alzaabi-etal-2026-gahwa</identifier>
<location>
<url>https://aclanthology.org/2026.arabicnlp-main.16/</url>
</location>
<part>
<date>2026-10</date>
<extent unit="page">
<start>219</start>
<end>227</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Gahwa: A Computational Lexicon for Emirati Arabic
%A Alzaabi, Saeed
%A Khalifa, Salam
%A Saeed, Mostafa
%A Dibas, Shahd
%A Aldarmaki, Hanan
%A Habash, Nizar
%Y Abdul-Mageed, Muhammad
%Y Elsayed, Tamer
%Y Bouamor, Houda
%Y El-Beltagy, Samhaa
%Y Al-Khalifa, Hend
%Y Abdelali, Ahmed
%Y Elmadany, AbdelRahim
%Y El Mekki, Abdellah
%Y Darwish, Kareem
%Y Alkhereyf, Sakhar
%Y Luqman, Hamzah
%Y Khalifa, Salam
%Y Magdy, Samar
%Y Alyafeai, Zaid
%Y Hamed, Injy
%Y Zaghouani, Wajdi
%Y Zitouni, Imed
%S Proceedings of The Fourth Arabic Natural Language Processing Conference
%D 2026
%8 October
%I Association for Computational Linguistics
%C Budapest, Hungary
%@ 979-8-89176-473-6
%F alzaabi-etal-2026-gahwa
%X Emirati Arabic remains one of the least-resourced Arabic dialects, with lexical information scattered across corpora, morphological databases, and dictionaries developed under incompatible annotation schemes. We present Gahwa, a machine-readable lexicon constructed by extracting, enriching, and standardizing evidence from an annotated Emirati corpus, a Gulf Arabic verb database, and a Gulf Arabic Wiktionary, unifying their input into one lemma-POS keyed scheme. We evaluate Gahwa through automatic coverage analysis of three Emirati datasets, GumarAE, Mixat, and the Ramsa Corpus, against existing Arabic morphological resources, and through analysis of out-of-vocabulary (OOV) forms. Results show that Gahwa has high word coverage across the three datasets, achieving 89.1-94.2% effective dediacritized lemma-POS token coverage, while the remaining OOV cases primarily reflect lexical gaps, orthographic variations, fused expressions, and morphological gaps.
%U https://aclanthology.org/2026.arabicnlp-main.16/
%P 219-227
Markdown (Informal)
[Gahwa: A Computational Lexicon for Emirati Arabic](https://aclanthology.org/2026.arabicnlp-main.16/) (Alzaabi et al., ArabicNLP 2026)
ACL
- Saeed Alzaabi, Salam Khalifa, Mostafa Saeed, Shahd Dibas, Hanan Aldarmaki, and Nizar Habash. 2026. Gahwa: A Computational Lexicon for Emirati Arabic. In Proceedings of The Fourth Arabic Natural Language Processing Conference, pages 219–227, Budapest, Hungary. Association for Computational Linguistics.