@inproceedings{koufakou-etal-2020-florunito,
title = "{F}lor{U}ni{T}o@{TRAC}-2: Retrofitting Word Embeddings on an Abusive Lexicon for Aggressive Language Detection",
author = "Koufakou, Anna and
Basile, Valerio and
Patti, Viviana",
editor = "Kumar, Ritesh and
Ojha, Atul Kr. and
Lahiri, Bornini and
Zampieri, Marcos and
Malmasi, Shervin and
Murdock, Vanessa and
Kadar, Daniel",
booktitle = "Proceedings of the Second Workshop on Trolling, Aggression and Cyberbullying",
month = may,
year = "2020",
address = "Marseille, France",
publisher = "European Language Resources Association (ELRA)",
url = "https://aclanthology.org/2020.trac-1.17",
pages = "106--112",
abstract = "This paper describes our participation to the TRAC-2 Shared Tasks on Aggression Identification. Our team, FlorUniTo, investigated the applicability of using an abusive lexicon to enhance word embeddings towards improving detection of aggressive language. The embeddings used in our paper are word-aligned pre-trained vectors for English, Hindi, and Bengali, to reflect the languages in the shared task data sets. The embeddings are retrofitted to a multilingual abusive lexicon, HurtLex. We experimented with an LSTM model using the original as well as the transformed embeddings and different language and setting variations. Overall, our systems placed toward the middle of the official rankings based on weighted F1 score. However, the results on the development and test sets show promising improvements across languages, especially on the misogynistic aggression sub-task.",
language = "English",
ISBN = "979-10-95546-56-6",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="koufakou-etal-2020-florunito">
<titleInfo>
<title>FlorUniTo@TRAC-2: Retrofitting Word Embeddings on an Abusive Lexicon for Aggressive Language Detection</title>
</titleInfo>
<name type="personal">
<namePart type="given">Anna</namePart>
<namePart type="family">Koufakou</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Valerio</namePart>
<namePart type="family">Basile</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Viviana</namePart>
<namePart type="family">Patti</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 Second Workshop on Trolling, Aggression and Cyberbullying</title>
</titleInfo>
<name type="personal">
<namePart type="given">Ritesh</namePart>
<namePart type="family">Kumar</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Atul</namePart>
<namePart type="given">Kr.</namePart>
<namePart type="family">Ojha</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Bornini</namePart>
<namePart type="family">Lahiri</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Marcos</namePart>
<namePart type="family">Zampieri</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Shervin</namePart>
<namePart type="family">Malmasi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Vanessa</namePart>
<namePart type="family">Murdock</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Daniel</namePart>
<namePart type="family">Kadar</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>European Language Resources Association (ELRA)</publisher>
<place>
<placeTerm type="text">Marseille, France</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
<identifier type="isbn">979-10-95546-56-6</identifier>
</relatedItem>
<abstract>This paper describes our participation to the TRAC-2 Shared Tasks on Aggression Identification. Our team, FlorUniTo, investigated the applicability of using an abusive lexicon to enhance word embeddings towards improving detection of aggressive language. The embeddings used in our paper are word-aligned pre-trained vectors for English, Hindi, and Bengali, to reflect the languages in the shared task data sets. The embeddings are retrofitted to a multilingual abusive lexicon, HurtLex. We experimented with an LSTM model using the original as well as the transformed embeddings and different language and setting variations. Overall, our systems placed toward the middle of the official rankings based on weighted F1 score. However, the results on the development and test sets show promising improvements across languages, especially on the misogynistic aggression sub-task.</abstract>
<identifier type="citekey">koufakou-etal-2020-florunito</identifier>
<location>
<url>https://aclanthology.org/2020.trac-1.17</url>
</location>
<part>
<date>2020-05</date>
<extent unit="page">
<start>106</start>
<end>112</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T FlorUniTo@TRAC-2: Retrofitting Word Embeddings on an Abusive Lexicon for Aggressive Language Detection
%A Koufakou, Anna
%A Basile, Valerio
%A Patti, Viviana
%Y Kumar, Ritesh
%Y Ojha, Atul Kr.
%Y Lahiri, Bornini
%Y Zampieri, Marcos
%Y Malmasi, Shervin
%Y Murdock, Vanessa
%Y Kadar, Daniel
%S Proceedings of the Second Workshop on Trolling, Aggression and Cyberbullying
%D 2020
%8 May
%I European Language Resources Association (ELRA)
%C Marseille, France
%@ 979-10-95546-56-6
%G English
%F koufakou-etal-2020-florunito
%X This paper describes our participation to the TRAC-2 Shared Tasks on Aggression Identification. Our team, FlorUniTo, investigated the applicability of using an abusive lexicon to enhance word embeddings towards improving detection of aggressive language. The embeddings used in our paper are word-aligned pre-trained vectors for English, Hindi, and Bengali, to reflect the languages in the shared task data sets. The embeddings are retrofitted to a multilingual abusive lexicon, HurtLex. We experimented with an LSTM model using the original as well as the transformed embeddings and different language and setting variations. Overall, our systems placed toward the middle of the official rankings based on weighted F1 score. However, the results on the development and test sets show promising improvements across languages, especially on the misogynistic aggression sub-task.
%U https://aclanthology.org/2020.trac-1.17
%P 106-112
Markdown (Informal)
[FlorUniTo@TRAC-2: Retrofitting Word Embeddings on an Abusive Lexicon for Aggressive Language Detection](https://aclanthology.org/2020.trac-1.17) (Koufakou et al., TRAC 2020)
ACL