@inproceedings{chowdhury-etal-2020-improving-arabic,
title = "Improving {A}rabic Text Categorization Using Transformer Training Diversification",
author = "Chowdhury, Shammur Absar and
Abdelali, Ahmed and
Darwish, Kareem and
Soon-Gyo, Jung and
Salminen, Joni and
Jansen, Bernard J.",
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-1.21",
pages = "226--236",
abstract = "Automatic categorization of short texts, such as news headlines and social media posts, has many applications ranging from content analysis to recommendation systems. In this paper, we use such text categorization i.e., labeling the social media posts to categories like {`}sports{'}, {`}politics{'}, {`}human-rights{'} among others, to showcase the efficacy of models across different sources and varieties of Arabic. In doing so, we show that diversifying the training data, whether by using diverse training data for the specific task (an increase of 21{\%} macro F1) or using diverse data to pre-train a BERT model (26{\%} macro F1), leads to overall improvements in classification effectiveness. In our work, we also introduce two new Arabic text categorization datasets, where the first is composed of social media posts from a popular Arabic news channel that cover Twitter, Facebook, and YouTube, and the second is composed of tweets from popular Arabic accounts. The posts in the former are nearly exclusively authored in modern standard Arabic (MSA), while the tweets in the latter contain both MSA and dialectal Arabic.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="chowdhury-etal-2020-improving-arabic">
<titleInfo>
<title>Improving Arabic Text Categorization Using Transformer Training Diversification</title>
</titleInfo>
<name type="personal">
<namePart type="given">Shammur</namePart>
<namePart type="given">Absar</namePart>
<namePart type="family">Chowdhury</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ahmed</namePart>
<namePart type="family">Abdelali</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Kareem</namePart>
<namePart type="family">Darwish</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jung</namePart>
<namePart type="family">Soon-Gyo</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Joni</namePart>
<namePart type="family">Salminen</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Bernard</namePart>
<namePart type="given">J</namePart>
<namePart type="family">Jansen</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>Automatic categorization of short texts, such as news headlines and social media posts, has many applications ranging from content analysis to recommendation systems. In this paper, we use such text categorization i.e., labeling the social media posts to categories like ‘sports’, ‘politics’, ‘human-rights’ among others, to showcase the efficacy of models across different sources and varieties of Arabic. In doing so, we show that diversifying the training data, whether by using diverse training data for the specific task (an increase of 21% macro F1) or using diverse data to pre-train a BERT model (26% macro F1), leads to overall improvements in classification effectiveness. In our work, we also introduce two new Arabic text categorization datasets, where the first is composed of social media posts from a popular Arabic news channel that cover Twitter, Facebook, and YouTube, and the second is composed of tweets from popular Arabic accounts. The posts in the former are nearly exclusively authored in modern standard Arabic (MSA), while the tweets in the latter contain both MSA and dialectal Arabic.</abstract>
<identifier type="citekey">chowdhury-etal-2020-improving-arabic</identifier>
<location>
<url>https://aclanthology.org/2020.wanlp-1.21</url>
</location>
<part>
<date>2020-12</date>
<extent unit="page">
<start>226</start>
<end>236</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Improving Arabic Text Categorization Using Transformer Training Diversification
%A Chowdhury, Shammur Absar
%A Abdelali, Ahmed
%A Darwish, Kareem
%A Soon-Gyo, Jung
%A Salminen, Joni
%A Jansen, Bernard J.
%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 chowdhury-etal-2020-improving-arabic
%X Automatic categorization of short texts, such as news headlines and social media posts, has many applications ranging from content analysis to recommendation systems. In this paper, we use such text categorization i.e., labeling the social media posts to categories like ‘sports’, ‘politics’, ‘human-rights’ among others, to showcase the efficacy of models across different sources and varieties of Arabic. In doing so, we show that diversifying the training data, whether by using diverse training data for the specific task (an increase of 21% macro F1) or using diverse data to pre-train a BERT model (26% macro F1), leads to overall improvements in classification effectiveness. In our work, we also introduce two new Arabic text categorization datasets, where the first is composed of social media posts from a popular Arabic news channel that cover Twitter, Facebook, and YouTube, and the second is composed of tweets from popular Arabic accounts. The posts in the former are nearly exclusively authored in modern standard Arabic (MSA), while the tweets in the latter contain both MSA and dialectal Arabic.
%U https://aclanthology.org/2020.wanlp-1.21
%P 226-236
Markdown (Informal)
[Improving Arabic Text Categorization Using Transformer Training Diversification](https://aclanthology.org/2020.wanlp-1.21) (Chowdhury et al., WANLP 2020)
ACL