@inproceedings{uzan-hacohen-kerner-2020-jct,
title = "{JCT} at {S}em{E}val-2020 Task 12: Offensive Language Detection in Tweets Using Preprocessing Methods, Character and Word N-grams",
author = "Uzan, Moshe and
HaCohen-Kerner, Yaakov",
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-1.266/",
doi = "10.18653/v1/2020.semeval-1.266",
pages = "2017--2022",
abstract = "In this paper, we describe our submissions to SemEval-2020 contest. We tackled subtask 12 - {\textquotedblleft}Multilingual Offensive Language Identification in Social Media{\textquotedblright}. We developed different models for four languages: Arabic, Danish, Greek, and Turkish. We applied three supervised machine learning methods using various combinations of character and word n-gram features. In addition, we applied various combinations of basic preprocessing methods. Our best submission was a model we built for offensive language identification in Danish using Random Forest. This model was ranked at the 6 position out of 39 submissions. Our result is lower by only 0.0025 than the result of the team that won the 4 place using entirely non-neural methods. Our experiments indicate that char ngram features are more helpful than word ngram features. This phenomenon probably occurs because tweets are more characterized by characters than by words, tweets are short, and contain various special sequences of characters, e.g., hashtags, shortcuts, slang words, and typos."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="uzan-hacohen-kerner-2020-jct">
<titleInfo>
<title>JCT at SemEval-2020 Task 12: Offensive Language Detection in Tweets Using Preprocessing Methods, Character and Word N-grams</title>
</titleInfo>
<name type="personal">
<namePart type="given">Moshe</namePart>
<namePart type="family">Uzan</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yaakov</namePart>
<namePart type="family">HaCohen-Kerner</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>In this paper, we describe our submissions to SemEval-2020 contest. We tackled subtask 12 - “Multilingual Offensive Language Identification in Social Media”. We developed different models for four languages: Arabic, Danish, Greek, and Turkish. We applied three supervised machine learning methods using various combinations of character and word n-gram features. In addition, we applied various combinations of basic preprocessing methods. Our best submission was a model we built for offensive language identification in Danish using Random Forest. This model was ranked at the 6 position out of 39 submissions. Our result is lower by only 0.0025 than the result of the team that won the 4 place using entirely non-neural methods. Our experiments indicate that char ngram features are more helpful than word ngram features. This phenomenon probably occurs because tweets are more characterized by characters than by words, tweets are short, and contain various special sequences of characters, e.g., hashtags, shortcuts, slang words, and typos.</abstract>
<identifier type="citekey">uzan-hacohen-kerner-2020-jct</identifier>
<identifier type="doi">10.18653/v1/2020.semeval-1.266</identifier>
<location>
<url>https://aclanthology.org/2020.semeval-1.266/</url>
</location>
<part>
<date>2020-12</date>
<extent unit="page">
<start>2017</start>
<end>2022</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T JCT at SemEval-2020 Task 12: Offensive Language Detection in Tweets Using Preprocessing Methods, Character and Word N-grams
%A Uzan, Moshe
%A HaCohen-Kerner, Yaakov
%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 uzan-hacohen-kerner-2020-jct
%X In this paper, we describe our submissions to SemEval-2020 contest. We tackled subtask 12 - “Multilingual Offensive Language Identification in Social Media”. We developed different models for four languages: Arabic, Danish, Greek, and Turkish. We applied three supervised machine learning methods using various combinations of character and word n-gram features. In addition, we applied various combinations of basic preprocessing methods. Our best submission was a model we built for offensive language identification in Danish using Random Forest. This model was ranked at the 6 position out of 39 submissions. Our result is lower by only 0.0025 than the result of the team that won the 4 place using entirely non-neural methods. Our experiments indicate that char ngram features are more helpful than word ngram features. This phenomenon probably occurs because tweets are more characterized by characters than by words, tweets are short, and contain various special sequences of characters, e.g., hashtags, shortcuts, slang words, and typos.
%R 10.18653/v1/2020.semeval-1.266
%U https://aclanthology.org/2020.semeval-1.266/
%U https://doi.org/10.18653/v1/2020.semeval-1.266
%P 2017-2022
Markdown (Informal)
[JCT at SemEval-2020 Task 12: Offensive Language Detection in Tweets Using Preprocessing Methods, Character and Word N-grams](https://aclanthology.org/2020.semeval-1.266/) (Uzan & HaCohen-Kerner, SemEval 2020)
ACL