@inproceedings{pavlopoulos-etal-2019-convai,
title = "{C}onv{AI} at {S}em{E}val-2019 Task 6: Offensive Language Identification and Categorization with Perspective and {BERT}",
author = "Pavlopoulos, John and
Thain, Nithum and
Dixon, Lucas and
Androutsopoulos, Ion",
editor = "May, Jonathan and
Shutova, Ekaterina and
Herbelot, Aurelie and
Zhu, Xiaodan and
Apidianaki, Marianna and
Mohammad, Saif M.",
booktitle = "Proceedings of the 13th International Workshop on Semantic Evaluation",
month = jun,
year = "2019",
address = "Minneapolis, Minnesota, USA",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/S19-2102",
doi = "10.18653/v1/S19-2102",
pages = "571--576",
abstract = "This paper presents the application of two strong baseline systems for toxicity detection and evaluates their performance in identifying and categorizing offensive language in social media. PERSPECTIVE is an API, that serves multiple machine learning models for the improvement of conversations online, as well as a toxicity detection system, trained on a wide variety of comments from platforms across the Internet. BERT is a recently popular language representation model, fine tuned per task and achieving state of the art performance in multiple NLP tasks. PERSPECTIVE performed better than BERT in detecting toxicity, but BERT was much better in categorizing the offensive type. Both baselines were ranked surprisingly high in the SEMEVAL-2019 OFFENSEVAL competition, PERSPECTIVE in detecting an offensive post (12th) and BERT in categorizing it (11th). The main contribution of this paper is the assessment of two strong baselines for the identification (PERSPECTIVE) and the categorization (BERT) of offensive language with little or no additional training data.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="pavlopoulos-etal-2019-convai">
<titleInfo>
<title>ConvAI at SemEval-2019 Task 6: Offensive Language Identification and Categorization with Perspective and BERT</title>
</titleInfo>
<name type="personal">
<namePart type="given">John</namePart>
<namePart type="family">Pavlopoulos</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Nithum</namePart>
<namePart type="family">Thain</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Lucas</namePart>
<namePart type="family">Dixon</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ion</namePart>
<namePart type="family">Androutsopoulos</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2019-06</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 13th International Workshop on Semantic Evaluation</title>
</titleInfo>
<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>
<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">Marianna</namePart>
<namePart type="family">Apidianaki</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Saif</namePart>
<namePart type="given">M</namePart>
<namePart type="family">Mohammad</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Minneapolis, Minnesota, USA</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>This paper presents the application of two strong baseline systems for toxicity detection and evaluates their performance in identifying and categorizing offensive language in social media. PERSPECTIVE is an API, that serves multiple machine learning models for the improvement of conversations online, as well as a toxicity detection system, trained on a wide variety of comments from platforms across the Internet. BERT is a recently popular language representation model, fine tuned per task and achieving state of the art performance in multiple NLP tasks. PERSPECTIVE performed better than BERT in detecting toxicity, but BERT was much better in categorizing the offensive type. Both baselines were ranked surprisingly high in the SEMEVAL-2019 OFFENSEVAL competition, PERSPECTIVE in detecting an offensive post (12th) and BERT in categorizing it (11th). The main contribution of this paper is the assessment of two strong baselines for the identification (PERSPECTIVE) and the categorization (BERT) of offensive language with little or no additional training data.</abstract>
<identifier type="citekey">pavlopoulos-etal-2019-convai</identifier>
<identifier type="doi">10.18653/v1/S19-2102</identifier>
<location>
<url>https://aclanthology.org/S19-2102</url>
</location>
<part>
<date>2019-06</date>
<extent unit="page">
<start>571</start>
<end>576</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T ConvAI at SemEval-2019 Task 6: Offensive Language Identification and Categorization with Perspective and BERT
%A Pavlopoulos, John
%A Thain, Nithum
%A Dixon, Lucas
%A Androutsopoulos, Ion
%Y May, Jonathan
%Y Shutova, Ekaterina
%Y Herbelot, Aurelie
%Y Zhu, Xiaodan
%Y Apidianaki, Marianna
%Y Mohammad, Saif M.
%S Proceedings of the 13th International Workshop on Semantic Evaluation
%D 2019
%8 June
%I Association for Computational Linguistics
%C Minneapolis, Minnesota, USA
%F pavlopoulos-etal-2019-convai
%X This paper presents the application of two strong baseline systems for toxicity detection and evaluates their performance in identifying and categorizing offensive language in social media. PERSPECTIVE is an API, that serves multiple machine learning models for the improvement of conversations online, as well as a toxicity detection system, trained on a wide variety of comments from platforms across the Internet. BERT is a recently popular language representation model, fine tuned per task and achieving state of the art performance in multiple NLP tasks. PERSPECTIVE performed better than BERT in detecting toxicity, but BERT was much better in categorizing the offensive type. Both baselines were ranked surprisingly high in the SEMEVAL-2019 OFFENSEVAL competition, PERSPECTIVE in detecting an offensive post (12th) and BERT in categorizing it (11th). The main contribution of this paper is the assessment of two strong baselines for the identification (PERSPECTIVE) and the categorization (BERT) of offensive language with little or no additional training data.
%R 10.18653/v1/S19-2102
%U https://aclanthology.org/S19-2102
%U https://doi.org/10.18653/v1/S19-2102
%P 571-576
Markdown (Informal)
[ConvAI at SemEval-2019 Task 6: Offensive Language Identification and Categorization with Perspective and BERT](https://aclanthology.org/S19-2102) (Pavlopoulos et al., SemEval 2019)
ACL