@inproceedings{abujaber-etal-2021-lecun,
title = "{L}e{C}un at {S}em{E}val-2021 Task 6: Detecting Persuasion Techniques in Text Using Ensembled Pretrained Transformers and Data Augmentation",
author = "Abujaber, Dia and
Qarqaz, Ahmed and
Abdullah, Malak A.",
editor = "Palmer, Alexis and
Schneider, Nathan and
Schluter, Natalie and
Emerson, Guy and
Herbelot, Aurelie and
Zhu, Xiaodan",
booktitle = "Proceedings of the 15th International Workshop on Semantic Evaluation (SemEval-2021)",
month = aug,
year = "2021",
address = "Online",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2021.semeval-1.148",
doi = "10.18653/v1/2021.semeval-1.148",
pages = "1068--1074",
abstract = "We developed a system for task 6 sub-task 1 for detecting propaganda in memes. An external dataset and augmentation data-set were used to extend the official competition data-set. Data augmentation techniques were applied on the external data-set and competition data-set to come up with the augmented data-set. We trained 5 transformers (DeBERTa, and 4 RoBERTa) and ensembled them to make the prediction. We trained 1 RoBERTa model initially on the augmented data-set for a few epochs and then fine-tuned it on the competition data-set which improved the f1-micro up to 0.1 scores. After that, another initial RoBERTa model was trained on the external data-set merged with the augmented data-set for few epochs and fine-tuned it on the competition data-set. Furthermore, we ensembled the initial models with the models after fine-tuning. For the final model in the ensemble, we trained a DeBERTa model on the augmented data-set without fine-tuning it on the competition data-set. Finally, we averaged the output of each model in the ensemble to make the prediction.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="abujaber-etal-2021-lecun">
<titleInfo>
<title>LeCun at SemEval-2021 Task 6: Detecting Persuasion Techniques in Text Using Ensembled Pretrained Transformers and Data Augmentation</title>
</titleInfo>
<name type="personal">
<namePart type="given">Dia</namePart>
<namePart type="family">Abujaber</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ahmed</namePart>
<namePart type="family">Qarqaz</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Malak</namePart>
<namePart type="given">A</namePart>
<namePart type="family">Abdullah</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2021-08</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 15th International Workshop on Semantic Evaluation (SemEval-2021)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Alexis</namePart>
<namePart type="family">Palmer</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Nathan</namePart>
<namePart type="family">Schneider</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Natalie</namePart>
<namePart type="family">Schluter</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Guy</namePart>
<namePart type="family">Emerson</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Aurelie</namePart>
<namePart type="family">Herbelot</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Xiaodan</namePart>
<namePart type="family">Zhu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Online</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>We developed a system for task 6 sub-task 1 for detecting propaganda in memes. An external dataset and augmentation data-set were used to extend the official competition data-set. Data augmentation techniques were applied on the external data-set and competition data-set to come up with the augmented data-set. We trained 5 transformers (DeBERTa, and 4 RoBERTa) and ensembled them to make the prediction. We trained 1 RoBERTa model initially on the augmented data-set for a few epochs and then fine-tuned it on the competition data-set which improved the f1-micro up to 0.1 scores. After that, another initial RoBERTa model was trained on the external data-set merged with the augmented data-set for few epochs and fine-tuned it on the competition data-set. Furthermore, we ensembled the initial models with the models after fine-tuning. For the final model in the ensemble, we trained a DeBERTa model on the augmented data-set without fine-tuning it on the competition data-set. Finally, we averaged the output of each model in the ensemble to make the prediction.</abstract>
<identifier type="citekey">abujaber-etal-2021-lecun</identifier>
<identifier type="doi">10.18653/v1/2021.semeval-1.148</identifier>
<location>
<url>https://aclanthology.org/2021.semeval-1.148</url>
</location>
<part>
<date>2021-08</date>
<extent unit="page">
<start>1068</start>
<end>1074</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T LeCun at SemEval-2021 Task 6: Detecting Persuasion Techniques in Text Using Ensembled Pretrained Transformers and Data Augmentation
%A Abujaber, Dia
%A Qarqaz, Ahmed
%A Abdullah, Malak A.
%Y Palmer, Alexis
%Y Schneider, Nathan
%Y Schluter, Natalie
%Y Emerson, Guy
%Y Herbelot, Aurelie
%Y Zhu, Xiaodan
%S Proceedings of the 15th International Workshop on Semantic Evaluation (SemEval-2021)
%D 2021
%8 August
%I Association for Computational Linguistics
%C Online
%F abujaber-etal-2021-lecun
%X We developed a system for task 6 sub-task 1 for detecting propaganda in memes. An external dataset and augmentation data-set were used to extend the official competition data-set. Data augmentation techniques were applied on the external data-set and competition data-set to come up with the augmented data-set. We trained 5 transformers (DeBERTa, and 4 RoBERTa) and ensembled them to make the prediction. We trained 1 RoBERTa model initially on the augmented data-set for a few epochs and then fine-tuned it on the competition data-set which improved the f1-micro up to 0.1 scores. After that, another initial RoBERTa model was trained on the external data-set merged with the augmented data-set for few epochs and fine-tuned it on the competition data-set. Furthermore, we ensembled the initial models with the models after fine-tuning. For the final model in the ensemble, we trained a DeBERTa model on the augmented data-set without fine-tuning it on the competition data-set. Finally, we averaged the output of each model in the ensemble to make the prediction.
%R 10.18653/v1/2021.semeval-1.148
%U https://aclanthology.org/2021.semeval-1.148
%U https://doi.org/10.18653/v1/2021.semeval-1.148
%P 1068-1074
Markdown (Informal)
[LeCun at SemEval-2021 Task 6: Detecting Persuasion Techniques in Text Using Ensembled Pretrained Transformers and Data Augmentation](https://aclanthology.org/2021.semeval-1.148) (Abujaber et al., SemEval 2021)
ACL