@inproceedings{helwe-etal-2020-semi,
title = "A Semi-Supervised {BERT} Approach for {A}rabic Named Entity Recognition",
author = "Helwe, Chadi and
Dib, Ghassan and
Shamas, Mohsen and
Elbassuoni, Shady",
editor = "Zitouni, Imed and
Abdul-Mageed, Muhammad and
Bouamor, Houda and
Bougares, Fethi and
El-Haj, Mahmoud and
Tomeh, Nadi and
Zaghouani, Wajdi",
booktitle = "Proceedings of the Fifth Arabic Natural Language Processing Workshop",
month = dec,
year = "2020",
address = "Barcelona, Spain (Online)",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2020.wanlp-1.5/",
pages = "49--57",
abstract = "Named entity recognition (NER) plays a significant role in many applications such as information extraction, information retrieval, question answering, and even machine translation. Most of the work on NER using deep learning was done for non-Arabic languages like English and French, and only few studies focused on Arabic. This paper proposes a semi-supervised learning approach to train a BERT-based NER model using labeled and semi-labeled datasets. We compared our approach against various baselines, and state-of-the-art Arabic NER tools on three datasets: AQMAR, NEWS, and TWEETS. We report a significant improvement in F-measure for the AQMAR and the NEWS datasets, which are written in Modern Standard Arabic (MSA), and competitive results for the TWEETS dataset, which contains tweets that are mostly in the Egyptian dialect and contain many mistakes or misspellings."
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="helwe-etal-2020-semi">
<titleInfo>
<title>A Semi-Supervised BERT Approach for Arabic Named Entity Recognition</title>
</titleInfo>
<name type="personal">
<namePart type="given">Chadi</namePart>
<namePart type="family">Helwe</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ghassan</namePart>
<namePart type="family">Dib</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Mohsen</namePart>
<namePart type="family">Shamas</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Shady</namePart>
<namePart type="family">Elbassuoni</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2020-12</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the Fifth Arabic Natural Language Processing Workshop</title>
</titleInfo>
<name type="personal">
<namePart type="given">Imed</namePart>
<namePart type="family">Zitouni</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<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">Houda</namePart>
<namePart type="family">Bouamor</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">Mahmoud</namePart>
<namePart type="family">El-Haj</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">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">Barcelona, Spain (Online)</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Named entity recognition (NER) plays a significant role in many applications such as information extraction, information retrieval, question answering, and even machine translation. Most of the work on NER using deep learning was done for non-Arabic languages like English and French, and only few studies focused on Arabic. This paper proposes a semi-supervised learning approach to train a BERT-based NER model using labeled and semi-labeled datasets. We compared our approach against various baselines, and state-of-the-art Arabic NER tools on three datasets: AQMAR, NEWS, and TWEETS. We report a significant improvement in F-measure for the AQMAR and the NEWS datasets, which are written in Modern Standard Arabic (MSA), and competitive results for the TWEETS dataset, which contains tweets that are mostly in the Egyptian dialect and contain many mistakes or misspellings.</abstract>
<identifier type="citekey">helwe-etal-2020-semi</identifier>
<location>
<url>https://aclanthology.org/2020.wanlp-1.5/</url>
</location>
<part>
<date>2020-12</date>
<extent unit="page">
<start>49</start>
<end>57</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T A Semi-Supervised BERT Approach for Arabic Named Entity Recognition
%A Helwe, Chadi
%A Dib, Ghassan
%A Shamas, Mohsen
%A Elbassuoni, Shady
%Y Zitouni, Imed
%Y Abdul-Mageed, Muhammad
%Y Bouamor, Houda
%Y Bougares, Fethi
%Y El-Haj, Mahmoud
%Y Tomeh, Nadi
%Y Zaghouani, Wajdi
%S Proceedings of the Fifth Arabic Natural Language Processing Workshop
%D 2020
%8 December
%I Association for Computational Linguistics
%C Barcelona, Spain (Online)
%F helwe-etal-2020-semi
%X Named entity recognition (NER) plays a significant role in many applications such as information extraction, information retrieval, question answering, and even machine translation. Most of the work on NER using deep learning was done for non-Arabic languages like English and French, and only few studies focused on Arabic. This paper proposes a semi-supervised learning approach to train a BERT-based NER model using labeled and semi-labeled datasets. We compared our approach against various baselines, and state-of-the-art Arabic NER tools on three datasets: AQMAR, NEWS, and TWEETS. We report a significant improvement in F-measure for the AQMAR and the NEWS datasets, which are written in Modern Standard Arabic (MSA), and competitive results for the TWEETS dataset, which contains tweets that are mostly in the Egyptian dialect and contain many mistakes or misspellings.
%U https://aclanthology.org/2020.wanlp-1.5/
%P 49-57
Markdown (Informal)
[A Semi-Supervised BERT Approach for Arabic Named Entity Recognition](https://aclanthology.org/2020.wanlp-1.5/) (Helwe et al., WANLP 2020)
ACL