@inproceedings{mulki-etal-2019-tw,
title = "Tw-{S}t{AR} at {S}em{E}val-2019 Task 5: N-gram embeddings for Hate Speech Detection in Multilingual Tweets",
author = "Mulki, Hala and
Bechikh Ali, Chedi and
Haddad, Hatem and
Babao{\u{g}}lu, Ismail",
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/S19-2090",
doi = "10.18653/v1/S19-2090",
pages = "503--507",
abstract = "In this paper, we describe our contribution in SemEval-2019: subtask A of task 5 {``}Multilingual detection of hate speech against immigrants and women in Twitter (HatEval){''}. We developed two hate speech detection model variants through Tw-StAR framework. While the first model adopted one-hot encoding ngrams to train an NB classifier, the second generated and learned n-gram embeddings within a feedforward neural network. For both models, specific terms, selected via MWT patterns, were tagged in the input data. With two feature types employed, we could investigate the ability of n-gram embeddings to rival one-hot n-grams. Our results showed that in English, n-gram embeddings outperformed one-hot ngrams. However, representing Spanish tweets by one-hot n-grams yielded a slightly better performance compared to that of n-gram embeddings. The official ranking indicated that Tw-StAR ranked 9th for English and 20th for Spanish.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="mulki-etal-2019-tw">
<titleInfo>
<title>Tw-StAR at SemEval-2019 Task 5: N-gram embeddings for Hate Speech Detection in Multilingual Tweets</title>
</titleInfo>
<name type="personal">
<namePart type="given">Hala</namePart>
<namePart type="family">Mulki</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Chedi</namePart>
<namePart type="family">Bechikh Ali</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Hatem</namePart>
<namePart type="family">Haddad</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ismail</namePart>
<namePart type="family">Babaoğlu</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>In this paper, we describe our contribution in SemEval-2019: subtask A of task 5 “Multilingual detection of hate speech against immigrants and women in Twitter (HatEval)”. We developed two hate speech detection model variants through Tw-StAR framework. While the first model adopted one-hot encoding ngrams to train an NB classifier, the second generated and learned n-gram embeddings within a feedforward neural network. For both models, specific terms, selected via MWT patterns, were tagged in the input data. With two feature types employed, we could investigate the ability of n-gram embeddings to rival one-hot n-grams. Our results showed that in English, n-gram embeddings outperformed one-hot ngrams. However, representing Spanish tweets by one-hot n-grams yielded a slightly better performance compared to that of n-gram embeddings. The official ranking indicated that Tw-StAR ranked 9th for English and 20th for Spanish.</abstract>
<identifier type="citekey">mulki-etal-2019-tw</identifier>
<identifier type="doi">10.18653/v1/S19-2090</identifier>
<location>
<url>https://aclanthology.org/S19-2090</url>
</location>
<part>
<date>2019-06</date>
<extent unit="page">
<start>503</start>
<end>507</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Tw-StAR at SemEval-2019 Task 5: N-gram embeddings for Hate Speech Detection in Multilingual Tweets
%A Mulki, Hala
%A Bechikh Ali, Chedi
%A Haddad, Hatem
%A Babaoğlu, Ismail
%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 mulki-etal-2019-tw
%X In this paper, we describe our contribution in SemEval-2019: subtask A of task 5 “Multilingual detection of hate speech against immigrants and women in Twitter (HatEval)”. We developed two hate speech detection model variants through Tw-StAR framework. While the first model adopted one-hot encoding ngrams to train an NB classifier, the second generated and learned n-gram embeddings within a feedforward neural network. For both models, specific terms, selected via MWT patterns, were tagged in the input data. With two feature types employed, we could investigate the ability of n-gram embeddings to rival one-hot n-grams. Our results showed that in English, n-gram embeddings outperformed one-hot ngrams. However, representing Spanish tweets by one-hot n-grams yielded a slightly better performance compared to that of n-gram embeddings. The official ranking indicated that Tw-StAR ranked 9th for English and 20th for Spanish.
%R 10.18653/v1/S19-2090
%U https://aclanthology.org/S19-2090
%U https://doi.org/10.18653/v1/S19-2090
%P 503-507
Markdown (Informal)
[Tw-StAR at SemEval-2019 Task 5: N-gram embeddings for Hate Speech Detection in Multilingual Tweets](https://aclanthology.org/S19-2090) (Mulki et al., SemEval 2019)
ACL