@inproceedings{dadu-pant-2020-team,
title = "Team Rouges at {S}em{E}val-2020 Task 12: Cross-lingual Inductive Transfer to Detect Offensive Language",
author = "Dadu, Tanvi and
Pant, Kartikey",
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-1.290",
doi = "10.18653/v1/2020.semeval-1.290",
pages = "2183--2189",
abstract = "With the growing use of social media and its availability, many instances of the use of offensive language have been observed across multiple languages and domains. This phenomenon has given rise to the growing need to detect the offensive language used in social media cross-lingually. In OffensEval 2020, the organizers have released the multilingual Offensive Language Identification Dataset (mOLID), which contains tweets in five different languages, to detect offensive language. In this work, we introduce a cross-lingual inductive approach to identify the offensive language in tweets using the contextual word embedding XLM-RoBERTa (XLM-R). We show that our model performs competitively on all five languages, obtaining the fourth position in the English task with an F1-score of 0.919 and eighth position in the Turkish task with an F1-score of 0.781. Further experimentation proves that our model works competitively in a zero-shot learning environment, and is extensible to other languages.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="dadu-pant-2020-team">
<titleInfo>
<title>Team Rouges at SemEval-2020 Task 12: Cross-lingual Inductive Transfer to Detect Offensive Language</title>
</titleInfo>
<name type="personal">
<namePart type="given">Tanvi</namePart>
<namePart type="family">Dadu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Kartikey</namePart>
<namePart type="family">Pant</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>With the growing use of social media and its availability, many instances of the use of offensive language have been observed across multiple languages and domains. This phenomenon has given rise to the growing need to detect the offensive language used in social media cross-lingually. In OffensEval 2020, the organizers have released the multilingual Offensive Language Identification Dataset (mOLID), which contains tweets in five different languages, to detect offensive language. In this work, we introduce a cross-lingual inductive approach to identify the offensive language in tweets using the contextual word embedding XLM-RoBERTa (XLM-R). We show that our model performs competitively on all five languages, obtaining the fourth position in the English task with an F1-score of 0.919 and eighth position in the Turkish task with an F1-score of 0.781. Further experimentation proves that our model works competitively in a zero-shot learning environment, and is extensible to other languages.</abstract>
<identifier type="citekey">dadu-pant-2020-team</identifier>
<identifier type="doi">10.18653/v1/2020.semeval-1.290</identifier>
<location>
<url>https://aclanthology.org/2020.semeval-1.290</url>
</location>
<part>
<date>2020-12</date>
<extent unit="page">
<start>2183</start>
<end>2189</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Team Rouges at SemEval-2020 Task 12: Cross-lingual Inductive Transfer to Detect Offensive Language
%A Dadu, Tanvi
%A Pant, Kartikey
%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 dadu-pant-2020-team
%X With the growing use of social media and its availability, many instances of the use of offensive language have been observed across multiple languages and domains. This phenomenon has given rise to the growing need to detect the offensive language used in social media cross-lingually. In OffensEval 2020, the organizers have released the multilingual Offensive Language Identification Dataset (mOLID), which contains tweets in five different languages, to detect offensive language. In this work, we introduce a cross-lingual inductive approach to identify the offensive language in tweets using the contextual word embedding XLM-RoBERTa (XLM-R). We show that our model performs competitively on all five languages, obtaining the fourth position in the English task with an F1-score of 0.919 and eighth position in the Turkish task with an F1-score of 0.781. Further experimentation proves that our model works competitively in a zero-shot learning environment, and is extensible to other languages.
%R 10.18653/v1/2020.semeval-1.290
%U https://aclanthology.org/2020.semeval-1.290
%U https://doi.org/10.18653/v1/2020.semeval-1.290
%P 2183-2189
Markdown (Informal)
[Team Rouges at SemEval-2020 Task 12: Cross-lingual Inductive Transfer to Detect Offensive Language](https://aclanthology.org/2020.semeval-1.290) (Dadu & Pant, SemEval 2020)
ACL