@inproceedings{garcia-diaz-etal-2022-umuteam-lt,
title = "{UMUT}eam@{LT}-{EDI}-{ACL}2022: Detecting homophobic and transphobic comments in {T}amil",
author = "Garc{\'\i}a-D{\'\i}az, Jos{\'e} and
Caparros-Laiz, Camilo and
Valencia-Garc{\'\i}a, Rafael",
editor = "Chakravarthi, Bharathi Raja and
Bharathi, B and
McCrae, John P and
Zarrouk, Manel and
Bali, Kalika and
Buitelaar, Paul",
booktitle = "Proceedings of the Second Workshop on Language Technology for Equality, Diversity and Inclusion",
month = may,
year = "2022",
address = "Dublin, Ireland",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2022.ltedi-1.16",
doi = "10.18653/v1/2022.ltedi-1.16",
pages = "140--144",
abstract = "This working-notes are about the participation of the UMUTeam in a LT-EDI shared task concerning the identification of homophobic and transphobic comments in YouTube. These comments are written in English, which has high availability to machine-learning resources; Tamil, which has fewer resources; and a transliteration from Tamil to Roman script combined with English sentences. To carry out this shared task, we train a neural network that combines several feature sets applying a knowledge integration strategy. These features are linguistic features extracted from a tool developed by our research group and contextual and non-contextual sentence embeddings. We ranked 7th for English subtask (macro f1-score of 45{\%}), 3rd for Tamil subtask (macro f1-score of 82{\%}), and 2nd for Tamil-English subtask (macro f1-score of 58{\%}).",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="garcia-diaz-etal-2022-umuteam-lt">
<titleInfo>
<title>UMUTeam@LT-EDI-ACL2022: Detecting homophobic and transphobic comments in Tamil</title>
</titleInfo>
<name type="personal">
<namePart type="given">José</namePart>
<namePart type="family">García-Díaz</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Camilo</namePart>
<namePart type="family">Caparros-Laiz</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Rafael</namePart>
<namePart type="family">Valencia-García</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2022-05</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the Second Workshop on Language Technology for Equality, Diversity and Inclusion</title>
</titleInfo>
<name type="personal">
<namePart type="given">Bharathi</namePart>
<namePart type="given">Raja</namePart>
<namePart type="family">Chakravarthi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">B</namePart>
<namePart type="family">Bharathi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">John</namePart>
<namePart type="given">P</namePart>
<namePart type="family">McCrae</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Manel</namePart>
<namePart type="family">Zarrouk</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Kalika</namePart>
<namePart type="family">Bali</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Paul</namePart>
<namePart type="family">Buitelaar</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Dublin, Ireland</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>This working-notes are about the participation of the UMUTeam in a LT-EDI shared task concerning the identification of homophobic and transphobic comments in YouTube. These comments are written in English, which has high availability to machine-learning resources; Tamil, which has fewer resources; and a transliteration from Tamil to Roman script combined with English sentences. To carry out this shared task, we train a neural network that combines several feature sets applying a knowledge integration strategy. These features are linguistic features extracted from a tool developed by our research group and contextual and non-contextual sentence embeddings. We ranked 7th for English subtask (macro f1-score of 45%), 3rd for Tamil subtask (macro f1-score of 82%), and 2nd for Tamil-English subtask (macro f1-score of 58%).</abstract>
<identifier type="citekey">garcia-diaz-etal-2022-umuteam-lt</identifier>
<identifier type="doi">10.18653/v1/2022.ltedi-1.16</identifier>
<location>
<url>https://aclanthology.org/2022.ltedi-1.16</url>
</location>
<part>
<date>2022-05</date>
<extent unit="page">
<start>140</start>
<end>144</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T UMUTeam@LT-EDI-ACL2022: Detecting homophobic and transphobic comments in Tamil
%A García-Díaz, José
%A Caparros-Laiz, Camilo
%A Valencia-García, Rafael
%Y Chakravarthi, Bharathi Raja
%Y Bharathi, B.
%Y McCrae, John P.
%Y Zarrouk, Manel
%Y Bali, Kalika
%Y Buitelaar, Paul
%S Proceedings of the Second Workshop on Language Technology for Equality, Diversity and Inclusion
%D 2022
%8 May
%I Association for Computational Linguistics
%C Dublin, Ireland
%F garcia-diaz-etal-2022-umuteam-lt
%X This working-notes are about the participation of the UMUTeam in a LT-EDI shared task concerning the identification of homophobic and transphobic comments in YouTube. These comments are written in English, which has high availability to machine-learning resources; Tamil, which has fewer resources; and a transliteration from Tamil to Roman script combined with English sentences. To carry out this shared task, we train a neural network that combines several feature sets applying a knowledge integration strategy. These features are linguistic features extracted from a tool developed by our research group and contextual and non-contextual sentence embeddings. We ranked 7th for English subtask (macro f1-score of 45%), 3rd for Tamil subtask (macro f1-score of 82%), and 2nd for Tamil-English subtask (macro f1-score of 58%).
%R 10.18653/v1/2022.ltedi-1.16
%U https://aclanthology.org/2022.ltedi-1.16
%U https://doi.org/10.18653/v1/2022.ltedi-1.16
%P 140-144
Markdown (Informal)
[UMUTeam@LT-EDI-ACL2022: Detecting homophobic and transphobic comments in Tamil](https://aclanthology.org/2022.ltedi-1.16) (García-Díaz et al., LTEDI 2022)
ACL