@inproceedings{alharbi-lee-2020-combining,
title = "Combining Character and Word Embeddings for the Detection of Offensive Language in {A}rabic",
author = "Alharbi, Abdullah I. and
Lee, Mark",
editor = "Al-Khalifa, Hend and
Magdy, Walid and
Darwish, Kareem and
Elsayed, Tamer and
Mubarak, Hamdy",
booktitle = "Proceedings of the 4th Workshop on Open-Source Arabic Corpora and Processing Tools, with a Shared Task on Offensive Language Detection",
month = may,
year = "2020",
address = "Marseille, France",
publisher = "European Language Resource Association",
url = "https://aclanthology.org/2020.osact-1.15",
pages = "91--96",
abstract = "Twitter and other social media platforms offer users the chance to share their ideas via short posts. While the easy exchange of ideas has value, these microblogs can be leveraged by people who want to share hatred. and such individuals can share negative views about an individual, race, or group with millions of people at the click of a button. There is thus an urgent need to establish a method that can automatically identify hate speech and offensive language. To contribute to this development, during the OSACT4 workshop, a shared task was undertaken to detect offensive language in Arabic. A key challenge was the uniqueness of the language used on social media, prompting the out-of-vocabulary (OOV) problem. In addition, the use of different dialects in Arabic exacerbates this problem. To deal with the issues associated with OOV, we generated a character-level embeddings model, which was trained on a massive data collected carefully. This level of embeddings can work effectively in resolving the problem of OOV words through its ability to learn the vectors of character n-grams or parts of words. The proposed systems were ranked 7th and 8th for Subtasks A and B, respectively.",
language = "English",
ISBN = "979-10-95546-51-1",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="alharbi-lee-2020-combining">
<titleInfo>
<title>Combining Character and Word Embeddings for the Detection of Offensive Language in Arabic</title>
</titleInfo>
<name type="personal">
<namePart type="given">Abdullah</namePart>
<namePart type="given">I</namePart>
<namePart type="family">Alharbi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Mark</namePart>
<namePart type="family">Lee</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2020-05</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<language>
<languageTerm type="text">English</languageTerm>
<languageTerm type="code" authority="iso639-2b">eng</languageTerm>
</language>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 4th Workshop on Open-Source Arabic Corpora and Processing Tools, with a Shared Task on Offensive Language Detection</title>
</titleInfo>
<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">Walid</namePart>
<namePart type="family">Magdy</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">Tamer</namePart>
<namePart type="family">Elsayed</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Hamdy</namePart>
<namePart type="family">Mubarak</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>European Language Resource Association</publisher>
<place>
<placeTerm type="text">Marseille, France</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
<identifier type="isbn">979-10-95546-51-1</identifier>
</relatedItem>
<abstract>Twitter and other social media platforms offer users the chance to share their ideas via short posts. While the easy exchange of ideas has value, these microblogs can be leveraged by people who want to share hatred. and such individuals can share negative views about an individual, race, or group with millions of people at the click of a button. There is thus an urgent need to establish a method that can automatically identify hate speech and offensive language. To contribute to this development, during the OSACT4 workshop, a shared task was undertaken to detect offensive language in Arabic. A key challenge was the uniqueness of the language used on social media, prompting the out-of-vocabulary (OOV) problem. In addition, the use of different dialects in Arabic exacerbates this problem. To deal with the issues associated with OOV, we generated a character-level embeddings model, which was trained on a massive data collected carefully. This level of embeddings can work effectively in resolving the problem of OOV words through its ability to learn the vectors of character n-grams or parts of words. The proposed systems were ranked 7th and 8th for Subtasks A and B, respectively.</abstract>
<identifier type="citekey">alharbi-lee-2020-combining</identifier>
<location>
<url>https://aclanthology.org/2020.osact-1.15</url>
</location>
<part>
<date>2020-05</date>
<extent unit="page">
<start>91</start>
<end>96</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Combining Character and Word Embeddings for the Detection of Offensive Language in Arabic
%A Alharbi, Abdullah I.
%A Lee, Mark
%Y Al-Khalifa, Hend
%Y Magdy, Walid
%Y Darwish, Kareem
%Y Elsayed, Tamer
%Y Mubarak, Hamdy
%S Proceedings of the 4th Workshop on Open-Source Arabic Corpora and Processing Tools, with a Shared Task on Offensive Language Detection
%D 2020
%8 May
%I European Language Resource Association
%C Marseille, France
%@ 979-10-95546-51-1
%G English
%F alharbi-lee-2020-combining
%X Twitter and other social media platforms offer users the chance to share their ideas via short posts. While the easy exchange of ideas has value, these microblogs can be leveraged by people who want to share hatred. and such individuals can share negative views about an individual, race, or group with millions of people at the click of a button. There is thus an urgent need to establish a method that can automatically identify hate speech and offensive language. To contribute to this development, during the OSACT4 workshop, a shared task was undertaken to detect offensive language in Arabic. A key challenge was the uniqueness of the language used on social media, prompting the out-of-vocabulary (OOV) problem. In addition, the use of different dialects in Arabic exacerbates this problem. To deal with the issues associated with OOV, we generated a character-level embeddings model, which was trained on a massive data collected carefully. This level of embeddings can work effectively in resolving the problem of OOV words through its ability to learn the vectors of character n-grams or parts of words. The proposed systems were ranked 7th and 8th for Subtasks A and B, respectively.
%U https://aclanthology.org/2020.osact-1.15
%P 91-96
Markdown (Informal)
[Combining Character and Word Embeddings for the Detection of Offensive Language in Arabic](https://aclanthology.org/2020.osact-1.15) (Alharbi & Lee, OSACT 2020)
ACL