@inproceedings{burtenshaw-kestemont-2021-uantwerp,
title = "{UA}ntwerp at {S}em{E}val-2021 Task 5: Spans are Spans, stacking a binary word level approach to toxic span detection",
author = "Burtenshaw, Ben and
Kestemont, Mike",
editor = "Palmer, Alexis and
Schneider, Nathan and
Schluter, Natalie and
Emerson, Guy and
Herbelot, Aurelie and
Zhu, Xiaodan",
booktitle = "Proceedings of the 15th International Workshop on Semantic Evaluation (SemEval-2021)",
month = aug,
year = "2021",
address = "Online",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2021.semeval-1.121",
doi = "10.18653/v1/2021.semeval-1.121",
pages = "898--903",
abstract = "This paper describes the system developed by the Antwerp Centre for Digital humanities and literary Criticism [UAntwerp] for toxic span detection. We used a stacked generalisation ensemble of five component models, with two distinct interpretations of the task. Two models attempted to predict binary word toxicity based on ngram sequences, whilst 3 categorical span based models were trained to predict toxic token labels based on complete sequence tokens. The five models{'} predictions were ensembled within an LSTM model. As well as describing the system, we perform error analysis to explore model performance in relation to textual features. The system described in this paper scored 0.6755 and ranked 26th.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="burtenshaw-kestemont-2021-uantwerp">
<titleInfo>
<title>UAntwerp at SemEval-2021 Task 5: Spans are Spans, stacking a binary word level approach to toxic span detection</title>
</titleInfo>
<name type="personal">
<namePart type="given">Ben</namePart>
<namePart type="family">Burtenshaw</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Mike</namePart>
<namePart type="family">Kestemont</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2021-08</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 15th International Workshop on Semantic Evaluation (SemEval-2021)</title>
</titleInfo>
<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">Natalie</namePart>
<namePart type="family">Schluter</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Guy</namePart>
<namePart type="family">Emerson</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>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Online</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>This paper describes the system developed by the Antwerp Centre for Digital humanities and literary Criticism [UAntwerp] for toxic span detection. We used a stacked generalisation ensemble of five component models, with two distinct interpretations of the task. Two models attempted to predict binary word toxicity based on ngram sequences, whilst 3 categorical span based models were trained to predict toxic token labels based on complete sequence tokens. The five models’ predictions were ensembled within an LSTM model. As well as describing the system, we perform error analysis to explore model performance in relation to textual features. The system described in this paper scored 0.6755 and ranked 26th.</abstract>
<identifier type="citekey">burtenshaw-kestemont-2021-uantwerp</identifier>
<identifier type="doi">10.18653/v1/2021.semeval-1.121</identifier>
<location>
<url>https://aclanthology.org/2021.semeval-1.121</url>
</location>
<part>
<date>2021-08</date>
<extent unit="page">
<start>898</start>
<end>903</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T UAntwerp at SemEval-2021 Task 5: Spans are Spans, stacking a binary word level approach to toxic span detection
%A Burtenshaw, Ben
%A Kestemont, Mike
%Y Palmer, Alexis
%Y Schneider, Nathan
%Y Schluter, Natalie
%Y Emerson, Guy
%Y Herbelot, Aurelie
%Y Zhu, Xiaodan
%S Proceedings of the 15th International Workshop on Semantic Evaluation (SemEval-2021)
%D 2021
%8 August
%I Association for Computational Linguistics
%C Online
%F burtenshaw-kestemont-2021-uantwerp
%X This paper describes the system developed by the Antwerp Centre for Digital humanities and literary Criticism [UAntwerp] for toxic span detection. We used a stacked generalisation ensemble of five component models, with two distinct interpretations of the task. Two models attempted to predict binary word toxicity based on ngram sequences, whilst 3 categorical span based models were trained to predict toxic token labels based on complete sequence tokens. The five models’ predictions were ensembled within an LSTM model. As well as describing the system, we perform error analysis to explore model performance in relation to textual features. The system described in this paper scored 0.6755 and ranked 26th.
%R 10.18653/v1/2021.semeval-1.121
%U https://aclanthology.org/2021.semeval-1.121
%U https://doi.org/10.18653/v1/2021.semeval-1.121
%P 898-903
Markdown (Informal)
[UAntwerp at SemEval-2021 Task 5: Spans are Spans, stacking a binary word level approach to toxic span detection](https://aclanthology.org/2021.semeval-1.121) (Burtenshaw & Kestemont, SemEval 2021)
ACL