@inproceedings{riabi-etal-2023-enriching,
title = "Enriching the {NA}rabizi Treebank: A Multifaceted Approach to Supporting an Under-Resourced Language",
author = "Riabi, Arij and
Mahamdi, Menel and
Seddah, Djam{\'e}",
editor = "Prange, Jakob and
Friedrich, Annemarie",
booktitle = "Proceedings of the 17th Linguistic Annotation Workshop (LAW-XVII)",
month = jul,
year = "2023",
address = "Toronto, Canada",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2023.law-1.26",
doi = "10.18653/v1/2023.law-1.26",
pages = "266--278",
abstract = "In this paper we address the scarcity of annotated data for NArabizi, a Romanized form of North African Arabic used mostly on social media, which poses challenges for Natural Language Processing (NLP). We introduce an enriched version of NArabizi Treebank (Seddah et al., 2020) with three main contributions: the addition of two novel annotation layers (named entity recognition and offensive language detection) and a re-annotation of the tokenization, morpho-syntactic and syntactic layers that ensure annotation consistency. Our experimental results, using different tokenization schemes, showcase the value of our contributions and highlight the impact of working with non-gold tokenization for NER and dependency parsing. To facilitate future research, we make these annotations publicly available. Our enhanced NArabizi Treebank paves the way for creating sophisticated language models and NLP tools for this under-represented language.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="riabi-etal-2023-enriching">
<titleInfo>
<title>Enriching the NArabizi Treebank: A Multifaceted Approach to Supporting an Under-Resourced Language</title>
</titleInfo>
<name type="personal">
<namePart type="given">Arij</namePart>
<namePart type="family">Riabi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Menel</namePart>
<namePart type="family">Mahamdi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Djamé</namePart>
<namePart type="family">Seddah</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2023-07</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 17th Linguistic Annotation Workshop (LAW-XVII)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Jakob</namePart>
<namePart type="family">Prange</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Annemarie</namePart>
<namePart type="family">Friedrich</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Toronto, Canada</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>In this paper we address the scarcity of annotated data for NArabizi, a Romanized form of North African Arabic used mostly on social media, which poses challenges for Natural Language Processing (NLP). We introduce an enriched version of NArabizi Treebank (Seddah et al., 2020) with three main contributions: the addition of two novel annotation layers (named entity recognition and offensive language detection) and a re-annotation of the tokenization, morpho-syntactic and syntactic layers that ensure annotation consistency. Our experimental results, using different tokenization schemes, showcase the value of our contributions and highlight the impact of working with non-gold tokenization for NER and dependency parsing. To facilitate future research, we make these annotations publicly available. Our enhanced NArabizi Treebank paves the way for creating sophisticated language models and NLP tools for this under-represented language.</abstract>
<identifier type="citekey">riabi-etal-2023-enriching</identifier>
<identifier type="doi">10.18653/v1/2023.law-1.26</identifier>
<location>
<url>https://aclanthology.org/2023.law-1.26</url>
</location>
<part>
<date>2023-07</date>
<extent unit="page">
<start>266</start>
<end>278</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Enriching the NArabizi Treebank: A Multifaceted Approach to Supporting an Under-Resourced Language
%A Riabi, Arij
%A Mahamdi, Menel
%A Seddah, Djamé
%Y Prange, Jakob
%Y Friedrich, Annemarie
%S Proceedings of the 17th Linguistic Annotation Workshop (LAW-XVII)
%D 2023
%8 July
%I Association for Computational Linguistics
%C Toronto, Canada
%F riabi-etal-2023-enriching
%X In this paper we address the scarcity of annotated data for NArabizi, a Romanized form of North African Arabic used mostly on social media, which poses challenges for Natural Language Processing (NLP). We introduce an enriched version of NArabizi Treebank (Seddah et al., 2020) with three main contributions: the addition of two novel annotation layers (named entity recognition and offensive language detection) and a re-annotation of the tokenization, morpho-syntactic and syntactic layers that ensure annotation consistency. Our experimental results, using different tokenization schemes, showcase the value of our contributions and highlight the impact of working with non-gold tokenization for NER and dependency parsing. To facilitate future research, we make these annotations publicly available. Our enhanced NArabizi Treebank paves the way for creating sophisticated language models and NLP tools for this under-represented language.
%R 10.18653/v1/2023.law-1.26
%U https://aclanthology.org/2023.law-1.26
%U https://doi.org/10.18653/v1/2023.law-1.26
%P 266-278
Markdown (Informal)
[Enriching the NArabizi Treebank: A Multifaceted Approach to Supporting an Under-Resourced Language](https://aclanthology.org/2023.law-1.26) (Riabi et al., LAW 2023)
ACL