@inproceedings{garcia-diaz-etal-2023-umuteam-sinai,
title = "{UMUT}eam and {SINAI} at {S}em{E}val-2023 Task 9: Multilingual Tweet Intimacy Analysis using Multilingual Large Language Models and Data Augmentation",
author = "Garc{\'\i}a-D{\'\i}az, Jos{\'e} Antonio and
Pan, Ronghao and
Jim{\'e}nez Zafra, Salud Mar{\'\i}a and
Martn-Valdivia, Mar{\'\i}a-Teresa and
Ure{\~n}a-L{\'o}pez, L. Alfonso and
Valencia-Garc{\'\i}a, Rafael",
editor = {Ojha, Atul Kr. and
Do{\u{g}}ru{\"o}z, A. Seza and
Da San Martino, Giovanni and
Tayyar Madabushi, Harish and
Kumar, Ritesh and
Sartori, Elisa},
booktitle = "Proceedings of the 17th International Workshop on Semantic Evaluation (SemEval-2023)",
month = jul,
year = "2023",
address = "Toronto, Canada",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2023.semeval-1.39",
doi = "10.18653/v1/2023.semeval-1.39",
pages = "293--299",
abstract = "This work presents the participation of the UMUTeam and the SINAI research groups in the SemEval-2023 Task 9: Multilingual Tweet Intimacy Analysis. The goal of this task is to predict the intimacy of a set of tweets in 10 languages: English, Spanish, Italian, Portuguese, French, Chinese, Hindi, Arabic, Dutch and Korean, of which, the last 4 are not in the training data. Our approach to address this task is based on data augmentation and the use of three multilingual Large Language Models (multilingual BERT, XLM and mDeBERTA) by ensemble learning. Our team ranked 30th out of 45 participants. Our best results were achieved with two unseen languages: Korean (16th) and Hindi (19th).",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="garcia-diaz-etal-2023-umuteam-sinai">
<titleInfo>
<title>UMUTeam and SINAI at SemEval-2023 Task 9: Multilingual Tweet Intimacy Analysis using Multilingual Large Language Models and Data Augmentation</title>
</titleInfo>
<name type="personal">
<namePart type="given">José</namePart>
<namePart type="given">Antonio</namePart>
<namePart type="family">García-Díaz</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ronghao</namePart>
<namePart type="family">Pan</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Salud</namePart>
<namePart type="given">María</namePart>
<namePart type="family">Jiménez Zafra</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">María-Teresa</namePart>
<namePart type="family">Martn-Valdivia</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">Rafael</namePart>
<namePart type="family">Valencia-García</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2023-07</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 17th International Workshop on Semantic Evaluation (SemEval-2023)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Atul</namePart>
<namePart type="given">Kr.</namePart>
<namePart type="family">Ojha</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">A</namePart>
<namePart type="given">Seza</namePart>
<namePart type="family">Doğruöz</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Giovanni</namePart>
<namePart type="family">Da San Martino</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Harish</namePart>
<namePart type="family">Tayyar Madabushi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ritesh</namePart>
<namePart type="family">Kumar</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Elisa</namePart>
<namePart type="family">Sartori</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Toronto, Canada</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>This work presents the participation of the UMUTeam and the SINAI research groups in the SemEval-2023 Task 9: Multilingual Tweet Intimacy Analysis. The goal of this task is to predict the intimacy of a set of tweets in 10 languages: English, Spanish, Italian, Portuguese, French, Chinese, Hindi, Arabic, Dutch and Korean, of which, the last 4 are not in the training data. Our approach to address this task is based on data augmentation and the use of three multilingual Large Language Models (multilingual BERT, XLM and mDeBERTA) by ensemble learning. Our team ranked 30th out of 45 participants. Our best results were achieved with two unseen languages: Korean (16th) and Hindi (19th).</abstract>
<identifier type="citekey">garcia-diaz-etal-2023-umuteam-sinai</identifier>
<identifier type="doi">10.18653/v1/2023.semeval-1.39</identifier>
<location>
<url>https://aclanthology.org/2023.semeval-1.39</url>
</location>
<part>
<date>2023-07</date>
<extent unit="page">
<start>293</start>
<end>299</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T UMUTeam and SINAI at SemEval-2023 Task 9: Multilingual Tweet Intimacy Analysis using Multilingual Large Language Models and Data Augmentation
%A García-Díaz, José Antonio
%A Pan, Ronghao
%A Jiménez Zafra, Salud María
%A Martn-Valdivia, María-Teresa
%A Ureña-López, L. Alfonso
%A Valencia-García, Rafael
%Y Ojha, Atul Kr.
%Y Doğruöz, A. Seza
%Y Da San Martino, Giovanni
%Y Tayyar Madabushi, Harish
%Y Kumar, Ritesh
%Y Sartori, Elisa
%S Proceedings of the 17th International Workshop on Semantic Evaluation (SemEval-2023)
%D 2023
%8 July
%I Association for Computational Linguistics
%C Toronto, Canada
%F garcia-diaz-etal-2023-umuteam-sinai
%X This work presents the participation of the UMUTeam and the SINAI research groups in the SemEval-2023 Task 9: Multilingual Tweet Intimacy Analysis. The goal of this task is to predict the intimacy of a set of tweets in 10 languages: English, Spanish, Italian, Portuguese, French, Chinese, Hindi, Arabic, Dutch and Korean, of which, the last 4 are not in the training data. Our approach to address this task is based on data augmentation and the use of three multilingual Large Language Models (multilingual BERT, XLM and mDeBERTA) by ensemble learning. Our team ranked 30th out of 45 participants. Our best results were achieved with two unseen languages: Korean (16th) and Hindi (19th).
%R 10.18653/v1/2023.semeval-1.39
%U https://aclanthology.org/2023.semeval-1.39
%U https://doi.org/10.18653/v1/2023.semeval-1.39
%P 293-299
Markdown (Informal)
[UMUTeam and SINAI at SemEval-2023 Task 9: Multilingual Tweet Intimacy Analysis using Multilingual Large Language Models and Data Augmentation](https://aclanthology.org/2023.semeval-1.39) (García-Díaz et al., SemEval 2023)
ACL