@inproceedings{inoue-etal-2022-morphosyntactic,
title = "Morphosyntactic Tagging with Pre-trained Language Models for {A}rabic and its Dialects",
author = "Inoue, Go and
Khalifa, Salam and
Habash, Nizar",
editor = "Muresan, Smaranda and
Nakov, Preslav and
Villavicencio, Aline",
booktitle = "Findings of the Association for Computational Linguistics: ACL 2022",
month = may,
year = "2022",
address = "Dublin, Ireland",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2022.findings-acl.135",
doi = "10.18653/v1/2022.findings-acl.135",
pages = "1708--1719",
abstract = "We present state-of-the-art results on morphosyntactic tagging across different varieties of Arabic using fine-tuned pre-trained transformer language models. Our models consistently outperform existing systems in Modern Standard Arabic and all the Arabic dialects we study, achieving 2.6{\%} absolute improvement over the previous state-of-the-art in Modern Standard Arabic, 2.8{\%} in Gulf, 1.6{\%} in Egyptian, and 8.3{\%} in Levantine. We explore different training setups for fine-tuning pre-trained transformer language models, including training data size, the use of external linguistic resources, and the use of annotated data from other dialects in a low-resource scenario. Our results show that strategic fine-tuning using datasets from other high-resource dialects is beneficial for a low-resource dialect. Additionally, we show that high-quality morphological analyzers as external linguistic resources are beneficial especially in low-resource settings.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="inoue-etal-2022-morphosyntactic">
<titleInfo>
<title>Morphosyntactic Tagging with Pre-trained Language Models for Arabic and its Dialects</title>
</titleInfo>
<name type="personal">
<namePart type="given">Go</namePart>
<namePart type="family">Inoue</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">Nizar</namePart>
<namePart type="family">Habash</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2022-05</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Findings of the Association for Computational Linguistics: ACL 2022</title>
</titleInfo>
<name type="personal">
<namePart type="given">Smaranda</namePart>
<namePart type="family">Muresan</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Preslav</namePart>
<namePart type="family">Nakov</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Aline</namePart>
<namePart type="family">Villavicencio</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Dublin, Ireland</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>We present state-of-the-art results on morphosyntactic tagging across different varieties of Arabic using fine-tuned pre-trained transformer language models. Our models consistently outperform existing systems in Modern Standard Arabic and all the Arabic dialects we study, achieving 2.6% absolute improvement over the previous state-of-the-art in Modern Standard Arabic, 2.8% in Gulf, 1.6% in Egyptian, and 8.3% in Levantine. We explore different training setups for fine-tuning pre-trained transformer language models, including training data size, the use of external linguistic resources, and the use of annotated data from other dialects in a low-resource scenario. Our results show that strategic fine-tuning using datasets from other high-resource dialects is beneficial for a low-resource dialect. Additionally, we show that high-quality morphological analyzers as external linguistic resources are beneficial especially in low-resource settings.</abstract>
<identifier type="citekey">inoue-etal-2022-morphosyntactic</identifier>
<identifier type="doi">10.18653/v1/2022.findings-acl.135</identifier>
<location>
<url>https://aclanthology.org/2022.findings-acl.135</url>
</location>
<part>
<date>2022-05</date>
<extent unit="page">
<start>1708</start>
<end>1719</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Morphosyntactic Tagging with Pre-trained Language Models for Arabic and its Dialects
%A Inoue, Go
%A Khalifa, Salam
%A Habash, Nizar
%Y Muresan, Smaranda
%Y Nakov, Preslav
%Y Villavicencio, Aline
%S Findings of the Association for Computational Linguistics: ACL 2022
%D 2022
%8 May
%I Association for Computational Linguistics
%C Dublin, Ireland
%F inoue-etal-2022-morphosyntactic
%X We present state-of-the-art results on morphosyntactic tagging across different varieties of Arabic using fine-tuned pre-trained transformer language models. Our models consistently outperform existing systems in Modern Standard Arabic and all the Arabic dialects we study, achieving 2.6% absolute improvement over the previous state-of-the-art in Modern Standard Arabic, 2.8% in Gulf, 1.6% in Egyptian, and 8.3% in Levantine. We explore different training setups for fine-tuning pre-trained transformer language models, including training data size, the use of external linguistic resources, and the use of annotated data from other dialects in a low-resource scenario. Our results show that strategic fine-tuning using datasets from other high-resource dialects is beneficial for a low-resource dialect. Additionally, we show that high-quality morphological analyzers as external linguistic resources are beneficial especially in low-resource settings.
%R 10.18653/v1/2022.findings-acl.135
%U https://aclanthology.org/2022.findings-acl.135
%U https://doi.org/10.18653/v1/2022.findings-acl.135
%P 1708-1719
Markdown (Informal)
[Morphosyntactic Tagging with Pre-trained Language Models for Arabic and its Dialects](https://aclanthology.org/2022.findings-acl.135) (Inoue et al., Findings 2022)
ACL