@inproceedings{ranasinghe-zampieri-2020-multilingual,
title = "Multilingual Offensive Language Identification with Cross-lingual Embeddings",
author = "Ranasinghe, Tharindu and
Zampieri, Marcos",
editor = "Webber, Bonnie and
Cohn, Trevor and
He, Yulan and
Liu, Yang",
booktitle = "Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing (EMNLP)",
month = nov,
year = "2020",
address = "Online",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2020.emnlp-main.470",
doi = "10.18653/v1/2020.emnlp-main.470",
pages = "5838--5844",
abstract = "Offensive content is pervasive in social media and a reason for concern to companies and government organizations. Several studies have been recently published investigating methods to detect the various forms of such content (e.g. hate speech, cyberbulling, and cyberaggression). The clear majority of these studies deal with English partially because most annotated datasets available contain English data. In this paper, we take advantage of English data available by applying cross-lingual contextual word embeddings and transfer learning to make predictions in languages with less resources. We project predictions on comparable data in Bengali, Hindi, and Spanish and we report results of 0.8415 F1 macro for Bengali, 0.8568 F1 macro for Hindi, and 0.7513 F1 macro for Spanish. Finally, we show that our approach compares favorably to the best systems submitted to recent shared tasks on these three languages, confirming the robustness of cross-lingual contextual embeddings and transfer learning for this task.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="ranasinghe-zampieri-2020-multilingual">
<titleInfo>
<title>Multilingual Offensive Language Identification with Cross-lingual Embeddings</title>
</titleInfo>
<name type="personal">
<namePart type="given">Tharindu</namePart>
<namePart type="family">Ranasinghe</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Marcos</namePart>
<namePart type="family">Zampieri</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2020-11</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing (EMNLP)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Bonnie</namePart>
<namePart type="family">Webber</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Trevor</namePart>
<namePart type="family">Cohn</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yulan</namePart>
<namePart type="family">He</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yang</namePart>
<namePart type="family">Liu</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>Offensive content is pervasive in social media and a reason for concern to companies and government organizations. Several studies have been recently published investigating methods to detect the various forms of such content (e.g. hate speech, cyberbulling, and cyberaggression). The clear majority of these studies deal with English partially because most annotated datasets available contain English data. In this paper, we take advantage of English data available by applying cross-lingual contextual word embeddings and transfer learning to make predictions in languages with less resources. We project predictions on comparable data in Bengali, Hindi, and Spanish and we report results of 0.8415 F1 macro for Bengali, 0.8568 F1 macro for Hindi, and 0.7513 F1 macro for Spanish. Finally, we show that our approach compares favorably to the best systems submitted to recent shared tasks on these three languages, confirming the robustness of cross-lingual contextual embeddings and transfer learning for this task.</abstract>
<identifier type="citekey">ranasinghe-zampieri-2020-multilingual</identifier>
<identifier type="doi">10.18653/v1/2020.emnlp-main.470</identifier>
<location>
<url>https://aclanthology.org/2020.emnlp-main.470</url>
</location>
<part>
<date>2020-11</date>
<extent unit="page">
<start>5838</start>
<end>5844</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Multilingual Offensive Language Identification with Cross-lingual Embeddings
%A Ranasinghe, Tharindu
%A Zampieri, Marcos
%Y Webber, Bonnie
%Y Cohn, Trevor
%Y He, Yulan
%Y Liu, Yang
%S Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing (EMNLP)
%D 2020
%8 November
%I Association for Computational Linguistics
%C Online
%F ranasinghe-zampieri-2020-multilingual
%X Offensive content is pervasive in social media and a reason for concern to companies and government organizations. Several studies have been recently published investigating methods to detect the various forms of such content (e.g. hate speech, cyberbulling, and cyberaggression). The clear majority of these studies deal with English partially because most annotated datasets available contain English data. In this paper, we take advantage of English data available by applying cross-lingual contextual word embeddings and transfer learning to make predictions in languages with less resources. We project predictions on comparable data in Bengali, Hindi, and Spanish and we report results of 0.8415 F1 macro for Bengali, 0.8568 F1 macro for Hindi, and 0.7513 F1 macro for Spanish. Finally, we show that our approach compares favorably to the best systems submitted to recent shared tasks on these three languages, confirming the robustness of cross-lingual contextual embeddings and transfer learning for this task.
%R 10.18653/v1/2020.emnlp-main.470
%U https://aclanthology.org/2020.emnlp-main.470
%U https://doi.org/10.18653/v1/2020.emnlp-main.470
%P 5838-5844
Markdown (Informal)
[Multilingual Offensive Language Identification with Cross-lingual Embeddings](https://aclanthology.org/2020.emnlp-main.470) (Ranasinghe & Zampieri, EMNLP 2020)
ACL