@inproceedings{rusert-2021-nlp,
title = "{NLP}{\_}{UIOWA} at {S}emeval-2021 Task 5: Transferring Toxic Sets to Tag Toxic Spans",
author = "Rusert, Jonathan",
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-1.119/",
doi = "10.18653/v1/2021.semeval-1.119",
pages = "881--887",
abstract = "We leverage a BLSTM with attention to identify toxic spans in texts. We explore different dimensions which affect the model`s performance. The first dimension explored is the toxic set the model is trained on. Besides the provided dataset, we explore the transferability of 5 different toxic related sets, including offensive, toxic, abusive, and hate sets. We find that the solely offensive set shows the highest promise of transferability. The second dimension we explore is methodology, including leveraging attention, employing a greedy remove method, using a frequency ratio, and examining hybrid combinations of multiple methods. We conduct an error analysis to examine which types of toxic spans were missed and which were wrongly inferred as toxic along with the main reasons why they occurred. Finally, we extend our method via ensembles, which achieves our highest F1 score of 55.1."
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="rusert-2021-nlp">
<titleInfo>
<title>NLP_UIOWA at Semeval-2021 Task 5: Transferring Toxic Sets to Tag Toxic Spans</title>
</titleInfo>
<name type="personal">
<namePart type="given">Jonathan</namePart>
<namePart type="family">Rusert</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>We leverage a BLSTM with attention to identify toxic spans in texts. We explore different dimensions which affect the model‘s performance. The first dimension explored is the toxic set the model is trained on. Besides the provided dataset, we explore the transferability of 5 different toxic related sets, including offensive, toxic, abusive, and hate sets. We find that the solely offensive set shows the highest promise of transferability. The second dimension we explore is methodology, including leveraging attention, employing a greedy remove method, using a frequency ratio, and examining hybrid combinations of multiple methods. We conduct an error analysis to examine which types of toxic spans were missed and which were wrongly inferred as toxic along with the main reasons why they occurred. Finally, we extend our method via ensembles, which achieves our highest F1 score of 55.1.</abstract>
<identifier type="citekey">rusert-2021-nlp</identifier>
<identifier type="doi">10.18653/v1/2021.semeval-1.119</identifier>
<location>
<url>https://aclanthology.org/2021.semeval-1.119/</url>
</location>
<part>
<date>2021-08</date>
<extent unit="page">
<start>881</start>
<end>887</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T NLP_UIOWA at Semeval-2021 Task 5: Transferring Toxic Sets to Tag Toxic Spans
%A Rusert, Jonathan
%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 rusert-2021-nlp
%X We leverage a BLSTM with attention to identify toxic spans in texts. We explore different dimensions which affect the model‘s performance. The first dimension explored is the toxic set the model is trained on. Besides the provided dataset, we explore the transferability of 5 different toxic related sets, including offensive, toxic, abusive, and hate sets. We find that the solely offensive set shows the highest promise of transferability. The second dimension we explore is methodology, including leveraging attention, employing a greedy remove method, using a frequency ratio, and examining hybrid combinations of multiple methods. We conduct an error analysis to examine which types of toxic spans were missed and which were wrongly inferred as toxic along with the main reasons why they occurred. Finally, we extend our method via ensembles, which achieves our highest F1 score of 55.1.
%R 10.18653/v1/2021.semeval-1.119
%U https://aclanthology.org/2021.semeval-1.119/
%U https://doi.org/10.18653/v1/2021.semeval-1.119
%P 881-887
Markdown (Informal)
[NLP_UIOWA at Semeval-2021 Task 5: Transferring Toxic Sets to Tag Toxic Spans](https://aclanthology.org/2021.semeval-1.119/) (Rusert, SemEval 2021)
ACL