@inproceedings{laskar-etal-2022-cnlp,
title = "{CNLP}-{NITS}-{PP} at {WANLP} 2022 Shared Task: Propaganda Detection in {A}rabic using Data Augmentation and {A}ra{BERT} Pre-trained Model",
author = "Laskar, Sahinur Rahman and
Singh, Rahul and
Khilji, Abdullah Faiz Ur Rahman and
Manna, Riyanka and
Pakray, Partha and
Bandyopadhyay, Sivaji",
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-1.65",
doi = "10.18653/v1/2022.wanlp-1.65",
pages = "541--544",
abstract = "In today{'}s time, online users are regularly exposed to media posts that are propagandistic. Several strategies have been developed to promote safer media consumption in Arabic to combat this. However, there is a limited available multilabel annotated social media dataset. In this work, we have used a pre-trained AraBERT twitter-base model on an expanded train data via data augmentation. Our team CNLP-NITS-PP, has achieved the third rank in subtask 1 at WANLP-2022, for propaganda detection in Arabic (shared task) in terms of micro-F1 score of 0.602.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="laskar-etal-2022-cnlp">
<titleInfo>
<title>CNLP-NITS-PP at WANLP 2022 Shared Task: Propaganda Detection in Arabic using Data Augmentation and AraBERT Pre-trained Model</title>
</titleInfo>
<name type="personal">
<namePart type="given">Sahinur</namePart>
<namePart type="given">Rahman</namePart>
<namePart type="family">Laskar</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Rahul</namePart>
<namePart type="family">Singh</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Abdullah</namePart>
<namePart type="given">Faiz</namePart>
<namePart type="given">Ur</namePart>
<namePart type="given">Rahman</namePart>
<namePart type="family">Khilji</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Riyanka</namePart>
<namePart type="family">Manna</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Partha</namePart>
<namePart type="family">Pakray</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sivaji</namePart>
<namePart type="family">Bandyopadhyay</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>In today’s time, online users are regularly exposed to media posts that are propagandistic. Several strategies have been developed to promote safer media consumption in Arabic to combat this. However, there is a limited available multilabel annotated social media dataset. In this work, we have used a pre-trained AraBERT twitter-base model on an expanded train data via data augmentation. Our team CNLP-NITS-PP, has achieved the third rank in subtask 1 at WANLP-2022, for propaganda detection in Arabic (shared task) in terms of micro-F1 score of 0.602.</abstract>
<identifier type="citekey">laskar-etal-2022-cnlp</identifier>
<identifier type="doi">10.18653/v1/2022.wanlp-1.65</identifier>
<location>
<url>https://aclanthology.org/2022.wanlp-1.65</url>
</location>
<part>
<date>2022-12</date>
<extent unit="page">
<start>541</start>
<end>544</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T CNLP-NITS-PP at WANLP 2022 Shared Task: Propaganda Detection in Arabic using Data Augmentation and AraBERT Pre-trained Model
%A Laskar, Sahinur Rahman
%A Singh, Rahul
%A Khilji, Abdullah Faiz Ur Rahman
%A Manna, Riyanka
%A Pakray, Partha
%A Bandyopadhyay, Sivaji
%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 laskar-etal-2022-cnlp
%X In today’s time, online users are regularly exposed to media posts that are propagandistic. Several strategies have been developed to promote safer media consumption in Arabic to combat this. However, there is a limited available multilabel annotated social media dataset. In this work, we have used a pre-trained AraBERT twitter-base model on an expanded train data via data augmentation. Our team CNLP-NITS-PP, has achieved the third rank in subtask 1 at WANLP-2022, for propaganda detection in Arabic (shared task) in terms of micro-F1 score of 0.602.
%R 10.18653/v1/2022.wanlp-1.65
%U https://aclanthology.org/2022.wanlp-1.65
%U https://doi.org/10.18653/v1/2022.wanlp-1.65
%P 541-544
Markdown (Informal)
[CNLP-NITS-PP at WANLP 2022 Shared Task: Propaganda Detection in Arabic using Data Augmentation and AraBERT Pre-trained Model](https://aclanthology.org/2022.wanlp-1.65) (Laskar et al., WANLP 2022)
ACL