@inproceedings{benito-etal-2019-gsi,
title = "{GSI}-{UPM} at {S}em{E}val-2019 Task 5: Semantic Similarity and Word Embeddings for Multilingual Detection of Hate Speech Against Immigrants and Women on {T}witter",
author = "Benito, Diego and
Araque, Oscar and
Iglesias, Carlos A.",
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/S19-2070/",
doi = "10.18653/v1/S19-2070",
pages = "396--403",
abstract = "This paper describes the GSI-UPM system for SemEval-2019 Task 5, which tackles multilingual detection of hate speech on Twitter. The main contribution of the paper is the use of a method based on word embeddings and semantic similarity combined with traditional paradigms, such as n-grams, TF-IDF and POS. This combination of several features is fine-tuned through ablation tests, demonstrating the usefulness of different features. While our approach outperforms baseline classifiers on different sub-tasks, the best of our submitted runs reached the 5th position on the Spanish sub-task A."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="benito-etal-2019-gsi">
<titleInfo>
<title>GSI-UPM at SemEval-2019 Task 5: Semantic Similarity and Word Embeddings for Multilingual Detection of Hate Speech Against Immigrants and Women on Twitter</title>
</titleInfo>
<name type="personal">
<namePart type="given">Diego</namePart>
<namePart type="family">Benito</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Oscar</namePart>
<namePart type="family">Araque</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Carlos</namePart>
<namePart type="given">A</namePart>
<namePart type="family">Iglesias</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 describes the GSI-UPM system for SemEval-2019 Task 5, which tackles multilingual detection of hate speech on Twitter. The main contribution of the paper is the use of a method based on word embeddings and semantic similarity combined with traditional paradigms, such as n-grams, TF-IDF and POS. This combination of several features is fine-tuned through ablation tests, demonstrating the usefulness of different features. While our approach outperforms baseline classifiers on different sub-tasks, the best of our submitted runs reached the 5th position on the Spanish sub-task A.</abstract>
<identifier type="citekey">benito-etal-2019-gsi</identifier>
<identifier type="doi">10.18653/v1/S19-2070</identifier>
<location>
<url>https://aclanthology.org/S19-2070/</url>
</location>
<part>
<date>2019-06</date>
<extent unit="page">
<start>396</start>
<end>403</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T GSI-UPM at SemEval-2019 Task 5: Semantic Similarity and Word Embeddings for Multilingual Detection of Hate Speech Against Immigrants and Women on Twitter
%A Benito, Diego
%A Araque, Oscar
%A Iglesias, Carlos A.
%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 benito-etal-2019-gsi
%X This paper describes the GSI-UPM system for SemEval-2019 Task 5, which tackles multilingual detection of hate speech on Twitter. The main contribution of the paper is the use of a method based on word embeddings and semantic similarity combined with traditional paradigms, such as n-grams, TF-IDF and POS. This combination of several features is fine-tuned through ablation tests, demonstrating the usefulness of different features. While our approach outperforms baseline classifiers on different sub-tasks, the best of our submitted runs reached the 5th position on the Spanish sub-task A.
%R 10.18653/v1/S19-2070
%U https://aclanthology.org/S19-2070/
%U https://doi.org/10.18653/v1/S19-2070
%P 396-403
Markdown (Informal)
[GSI-UPM at SemEval-2019 Task 5: Semantic Similarity and Word Embeddings for Multilingual Detection of Hate Speech Against Immigrants and Women on Twitter](https://aclanthology.org/S19-2070/) (Benito et al., SemEval 2019)
ACL