@inproceedings{plaza-del-arco-etal-2021-sinai,
title = "{SINAI} at {S}em{E}val-2021 Task 5: Combining Embeddings in a {B}i{LSTM}-{CRF} model for Toxic Spans Detection",
author = "Plaza-del-Arco, Flor Miriam and
L{\'o}pez-{\'U}beda, Pilar and
Ure{\~n}a-L{\'o}pez, L. Alfonso and
Mart{\'\i}n-Valdivia, M. Teresa",
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-1.134",
doi = "10.18653/v1/2021.semeval-1.134",
pages = "984--989",
abstract = "This paper describes the participation of SINAI team at Task 5: Toxic Spans Detection which consists of identifying spans that make a text toxic. Although several resources and systems have been developed so far in the context of offensive language, both annotation and tasks have mainly focused on classifying whether a text is offensive or not. However, detecting toxic spans is crucial to identify why a text is toxic and can assist human moderators to locate this type of content on social media. In order to accomplish the task, we follow a deep learning-based approach using a Bidirectional variant of a Long Short Term Memory network along with a stacked Conditional Random Field decoding layer (BiLSTM-CRF). Specifically, we test the performance of the combination of different pre-trained word embeddings for recognizing toxic entities in text. The results show that the combination of word embeddings helps in detecting offensive content. Our team ranks 29th out of 91 participants.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="plaza-del-arco-etal-2021-sinai">
<titleInfo>
<title>SINAI at SemEval-2021 Task 5: Combining Embeddings in a BiLSTM-CRF model for Toxic Spans Detection</title>
</titleInfo>
<name type="personal">
<namePart type="given">Flor</namePart>
<namePart type="given">Miriam</namePart>
<namePart type="family">Plaza-del-Arco</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Pilar</namePart>
<namePart type="family">López-Úbeda</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">L</namePart>
<namePart type="given">Alfonso</namePart>
<namePart type="family">Ureña-López</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">M</namePart>
<namePart type="given">Teresa</namePart>
<namePart type="family">Martín-Valdivia</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 participation of SINAI team at Task 5: Toxic Spans Detection which consists of identifying spans that make a text toxic. Although several resources and systems have been developed so far in the context of offensive language, both annotation and tasks have mainly focused on classifying whether a text is offensive or not. However, detecting toxic spans is crucial to identify why a text is toxic and can assist human moderators to locate this type of content on social media. In order to accomplish the task, we follow a deep learning-based approach using a Bidirectional variant of a Long Short Term Memory network along with a stacked Conditional Random Field decoding layer (BiLSTM-CRF). Specifically, we test the performance of the combination of different pre-trained word embeddings for recognizing toxic entities in text. The results show that the combination of word embeddings helps in detecting offensive content. Our team ranks 29th out of 91 participants.</abstract>
<identifier type="citekey">plaza-del-arco-etal-2021-sinai</identifier>
<identifier type="doi">10.18653/v1/2021.semeval-1.134</identifier>
<location>
<url>https://aclanthology.org/2021.semeval-1.134</url>
</location>
<part>
<date>2021-08</date>
<extent unit="page">
<start>984</start>
<end>989</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T SINAI at SemEval-2021 Task 5: Combining Embeddings in a BiLSTM-CRF model for Toxic Spans Detection
%A Plaza-del-Arco, Flor Miriam
%A López-Úbeda, Pilar
%A Ureña-López, L. Alfonso
%A Martín-Valdivia, M. Teresa
%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 plaza-del-arco-etal-2021-sinai
%X This paper describes the participation of SINAI team at Task 5: Toxic Spans Detection which consists of identifying spans that make a text toxic. Although several resources and systems have been developed so far in the context of offensive language, both annotation and tasks have mainly focused on classifying whether a text is offensive or not. However, detecting toxic spans is crucial to identify why a text is toxic and can assist human moderators to locate this type of content on social media. In order to accomplish the task, we follow a deep learning-based approach using a Bidirectional variant of a Long Short Term Memory network along with a stacked Conditional Random Field decoding layer (BiLSTM-CRF). Specifically, we test the performance of the combination of different pre-trained word embeddings for recognizing toxic entities in text. The results show that the combination of word embeddings helps in detecting offensive content. Our team ranks 29th out of 91 participants.
%R 10.18653/v1/2021.semeval-1.134
%U https://aclanthology.org/2021.semeval-1.134
%U https://doi.org/10.18653/v1/2021.semeval-1.134
%P 984-989
Markdown (Informal)
[SINAI at SemEval-2021 Task 5: Combining Embeddings in a BiLSTM-CRF model for Toxic Spans Detection](https://aclanthology.org/2021.semeval-1.134) (Plaza-del-Arco et al., SemEval 2021)
ACL