@inproceedings{fashwan-alansary-2022-developing,
title = "Developing a Tag-Set and Extracting the Morphological Lexicons to Build a Morphological Analyzer for {E}gyptian {A}rabic",
author = "Fashwan, Amany and
Alansary, Sameh",
editor = "Bouamor, Houda and
Al-Khalifa, Hend and
Darwish, Kareem and
Rambow, Owen and
Bougares, Fethi and
Abdelali, Ahmed and
Tomeh, Nadi and
Khalifa, Salam and
Zaghouani, Wajdi",
booktitle = "Proceedings of the Seventh Arabic Natural Language Processing Workshop (WANLP)",
month = dec,
year = "2022",
address = "Abu Dhabi, United Arab Emirates (Hybrid)",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2022.wanlp-1.14/",
doi = "10.18653/v1/2022.wanlp-1.14",
pages = "142--160",
abstract = "This paper sheds light on an in-progress work for building a morphological analyzer for Egyptian Arabic (EGY). To build such a tool, a tag-set schema is developed depending on a corpus of 527,000 EGY words covering different sources and genres. This tag-set schema is used in annotating about 318,940 words, morphologically, according to their contexts. Each annotated word is associated with its suitable prefix(s), original stem, tag, suffix(s), glossary, number, gender, definiteness, and conventional lemma and stem. These morphologically annotated words, in turns, are used in developing the proposed morphological analyzer where the morphological lexicons and the compatibility tables are extracted and tested. The system is compared with one of best EGY morphological analyzers; CALIMA."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="fashwan-alansary-2022-developing">
<titleInfo>
<title>Developing a Tag-Set and Extracting the Morphological Lexicons to Build a Morphological Analyzer for Egyptian Arabic</title>
</titleInfo>
<name type="personal">
<namePart type="given">Amany</namePart>
<namePart type="family">Fashwan</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sameh</namePart>
<namePart type="family">Alansary</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2022-12</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the Seventh Arabic Natural Language Processing Workshop (WANLP)</title>
</titleInfo>
<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">Hend</namePart>
<namePart type="family">Al-Khalifa</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">Owen</namePart>
<namePart type="family">Rambow</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Fethi</namePart>
<namePart type="family">Bougares</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">Nadi</namePart>
<namePart type="family">Tomeh</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">Wajdi</namePart>
<namePart type="family">Zaghouani</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Abu Dhabi, United Arab Emirates (Hybrid)</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>This paper sheds light on an in-progress work for building a morphological analyzer for Egyptian Arabic (EGY). To build such a tool, a tag-set schema is developed depending on a corpus of 527,000 EGY words covering different sources and genres. This tag-set schema is used in annotating about 318,940 words, morphologically, according to their contexts. Each annotated word is associated with its suitable prefix(s), original stem, tag, suffix(s), glossary, number, gender, definiteness, and conventional lemma and stem. These morphologically annotated words, in turns, are used in developing the proposed morphological analyzer where the morphological lexicons and the compatibility tables are extracted and tested. The system is compared with one of best EGY morphological analyzers; CALIMA.</abstract>
<identifier type="citekey">fashwan-alansary-2022-developing</identifier>
<identifier type="doi">10.18653/v1/2022.wanlp-1.14</identifier>
<location>
<url>https://aclanthology.org/2022.wanlp-1.14/</url>
</location>
<part>
<date>2022-12</date>
<extent unit="page">
<start>142</start>
<end>160</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Developing a Tag-Set and Extracting the Morphological Lexicons to Build a Morphological Analyzer for Egyptian Arabic
%A Fashwan, Amany
%A Alansary, Sameh
%Y Bouamor, Houda
%Y Al-Khalifa, Hend
%Y Darwish, Kareem
%Y Rambow, Owen
%Y Bougares, Fethi
%Y Abdelali, Ahmed
%Y Tomeh, Nadi
%Y Khalifa, Salam
%Y Zaghouani, Wajdi
%S Proceedings of the Seventh Arabic Natural Language Processing Workshop (WANLP)
%D 2022
%8 December
%I Association for Computational Linguistics
%C Abu Dhabi, United Arab Emirates (Hybrid)
%F fashwan-alansary-2022-developing
%X This paper sheds light on an in-progress work for building a morphological analyzer for Egyptian Arabic (EGY). To build such a tool, a tag-set schema is developed depending on a corpus of 527,000 EGY words covering different sources and genres. This tag-set schema is used in annotating about 318,940 words, morphologically, according to their contexts. Each annotated word is associated with its suitable prefix(s), original stem, tag, suffix(s), glossary, number, gender, definiteness, and conventional lemma and stem. These morphologically annotated words, in turns, are used in developing the proposed morphological analyzer where the morphological lexicons and the compatibility tables are extracted and tested. The system is compared with one of best EGY morphological analyzers; CALIMA.
%R 10.18653/v1/2022.wanlp-1.14
%U https://aclanthology.org/2022.wanlp-1.14/
%U https://doi.org/10.18653/v1/2022.wanlp-1.14
%P 142-160
Markdown (Informal)
[Developing a Tag-Set and Extracting the Morphological Lexicons to Build a Morphological Analyzer for Egyptian Arabic](https://aclanthology.org/2022.wanlp-1.14/) (Fashwan & Alansary, WANLP 2022)
ACL