@inproceedings{alami-etal-2020-lisac,
title = "{LISAC} {FSDM}-{USMBA} Team at {S}em{E}val-2020 Task 12: Overcoming {A}ra{BERT}{'}s pretrain-finetune discrepancy for {A}rabic offensive language identification",
author = "Alami, Hamza and
Ouatik El Alaoui, Said and
Benlahbib, Abdessamad and
En-nahnahi, Noureddine",
editor = "Herbelot, Aurelie and
Zhu, Xiaodan and
Palmer, Alexis and
Schneider, Nathan and
May, Jonathan and
Shutova, Ekaterina",
booktitle = "Proceedings of the Fourteenth Workshop on Semantic Evaluation",
month = dec,
year = "2020",
address = "Barcelona (online)",
publisher = "International Committee for Computational Linguistics",
url = "https://aclanthology.org/2020.semeval-1.275",
doi = "10.18653/v1/2020.semeval-1.275",
pages = "2080--2085",
abstract = "AraBERT is an Arabic version of the state-of-the-art Bidirectional Encoder Representations from Transformers (BERT) model. The latter has achieved good performance in a variety of Natural Language Processing (NLP) tasks. In this paper, we propose an effective AraBERT embeddings-based method for dealing with offensive Arabic language in Twitter. First, we pre-process tweets by handling emojis and including their Arabic meanings. To overcome the pretrain-finetune discrepancy, we substitute each detected emojis by the special token [MASK] into both fine tuning and inference phases. Then, we represent tweets tokens by applying AraBERT model. Finally, we feed the tweet representation into a sigmoid function to decide whether a tweet is offensive or not. The proposed method achieved the best results on OffensEval 2020: Arabic task and reached a macro F1 score equal to 90.17{\%}.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="alami-etal-2020-lisac">
<titleInfo>
<title>LISAC FSDM-USMBA Team at SemEval-2020 Task 12: Overcoming AraBERT’s pretrain-finetune discrepancy for Arabic offensive language identification</title>
</titleInfo>
<name type="personal">
<namePart type="given">Hamza</namePart>
<namePart type="family">Alami</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Said</namePart>
<namePart type="family">Ouatik El Alaoui</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Abdessamad</namePart>
<namePart type="family">Benlahbib</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Noureddine</namePart>
<namePart type="family">En-nahnahi</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 Fourteenth Workshop on Semantic Evaluation</title>
</titleInfo>
<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>
<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">Jonathan</namePart>
<namePart type="family">May</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ekaterina</namePart>
<namePart type="family">Shutova</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>International Committee for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Barcelona (online)</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>AraBERT is an Arabic version of the state-of-the-art Bidirectional Encoder Representations from Transformers (BERT) model. The latter has achieved good performance in a variety of Natural Language Processing (NLP) tasks. In this paper, we propose an effective AraBERT embeddings-based method for dealing with offensive Arabic language in Twitter. First, we pre-process tweets by handling emojis and including their Arabic meanings. To overcome the pretrain-finetune discrepancy, we substitute each detected emojis by the special token [MASK] into both fine tuning and inference phases. Then, we represent tweets tokens by applying AraBERT model. Finally, we feed the tweet representation into a sigmoid function to decide whether a tweet is offensive or not. The proposed method achieved the best results on OffensEval 2020: Arabic task and reached a macro F1 score equal to 90.17%.</abstract>
<identifier type="citekey">alami-etal-2020-lisac</identifier>
<identifier type="doi">10.18653/v1/2020.semeval-1.275</identifier>
<location>
<url>https://aclanthology.org/2020.semeval-1.275</url>
</location>
<part>
<date>2020-12</date>
<extent unit="page">
<start>2080</start>
<end>2085</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T LISAC FSDM-USMBA Team at SemEval-2020 Task 12: Overcoming AraBERT’s pretrain-finetune discrepancy for Arabic offensive language identification
%A Alami, Hamza
%A Ouatik El Alaoui, Said
%A Benlahbib, Abdessamad
%A En-nahnahi, Noureddine
%Y Herbelot, Aurelie
%Y Zhu, Xiaodan
%Y Palmer, Alexis
%Y Schneider, Nathan
%Y May, Jonathan
%Y Shutova, Ekaterina
%S Proceedings of the Fourteenth Workshop on Semantic Evaluation
%D 2020
%8 December
%I International Committee for Computational Linguistics
%C Barcelona (online)
%F alami-etal-2020-lisac
%X AraBERT is an Arabic version of the state-of-the-art Bidirectional Encoder Representations from Transformers (BERT) model. The latter has achieved good performance in a variety of Natural Language Processing (NLP) tasks. In this paper, we propose an effective AraBERT embeddings-based method for dealing with offensive Arabic language in Twitter. First, we pre-process tweets by handling emojis and including their Arabic meanings. To overcome the pretrain-finetune discrepancy, we substitute each detected emojis by the special token [MASK] into both fine tuning and inference phases. Then, we represent tweets tokens by applying AraBERT model. Finally, we feed the tweet representation into a sigmoid function to decide whether a tweet is offensive or not. The proposed method achieved the best results on OffensEval 2020: Arabic task and reached a macro F1 score equal to 90.17%.
%R 10.18653/v1/2020.semeval-1.275
%U https://aclanthology.org/2020.semeval-1.275
%U https://doi.org/10.18653/v1/2020.semeval-1.275
%P 2080-2085
Markdown (Informal)
[LISAC FSDM-USMBA Team at SemEval-2020 Task 12: Overcoming AraBERT’s pretrain-finetune discrepancy for Arabic offensive language identification](https://aclanthology.org/2020.semeval-1.275) (Alami et al., SemEval 2020)
ACL