@inproceedings{garcia-diaz-etal-2023-umuteam,
title = "{UMUT}eam at {S}em{E}val-2023 Task 12: Ensemble Learning of {LLM}s applied to Sentiment Analysis for Low-resource {A}frican Languages",
author = "Garc{\'\i}a-D{\'\i}az, Jos{\'e} Antonio and
Caparros-laiz, Camilo and
Almela, {\'A}ngela and
Alcar{\'a}z-M{\'a}rmol, Gema and
Mar{\'\i}n-P{\'e}rez, Mar{\'\i}a Jos{\'e} 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-1.38",
doi = "10.18653/v1/2023.semeval-1.38",
pages = "285--292",
abstract = "These working notes summarize the participation of the UMUTeam in the SemEval 2023 shared task: AfriSenti, focused on Sentiment Analysis in several African languages. Two subtasks are proposed, one in which each language is considered separately and another one in which all languages are merged. Our proposal to solve both subtasks is grounded on the combination of features extracted from several multilingual Large Language Models and a subset of language-independent linguistic features. Our best results are achieved with the African languages less represented in the training set: Xitsonga, a Mozambique dialect, with a weighted f1-score of 54.89{\textbackslash}{\%}; Algerian Arabic, with a weighted f1-score of 68.52{\textbackslash}{\%}; Swahili, with a weighted f1-score of 60.52{\textbackslash}{\%}; and Twi, with a weighted f1-score of 71.14{\%}.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="garcia-diaz-etal-2023-umuteam">
<titleInfo>
<title>UMUTeam at SemEval-2023 Task 12: Ensemble Learning of LLMs applied to Sentiment Analysis for Low-resource African Languages</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">Camilo</namePart>
<namePart type="family">Caparros-laiz</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ángela</namePart>
<namePart type="family">Almela</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Gema</namePart>
<namePart type="family">Alcaráz-Mármol</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">María</namePart>
<namePart type="given">José</namePart>
<namePart type="family">Marín-Pérez</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>These working notes summarize the participation of the UMUTeam in the SemEval 2023 shared task: AfriSenti, focused on Sentiment Analysis in several African languages. Two subtasks are proposed, one in which each language is considered separately and another one in which all languages are merged. Our proposal to solve both subtasks is grounded on the combination of features extracted from several multilingual Large Language Models and a subset of language-independent linguistic features. Our best results are achieved with the African languages less represented in the training set: Xitsonga, a Mozambique dialect, with a weighted f1-score of 54.89\textbackslash%; Algerian Arabic, with a weighted f1-score of 68.52\textbackslash%; Swahili, with a weighted f1-score of 60.52\textbackslash%; and Twi, with a weighted f1-score of 71.14%.</abstract>
<identifier type="citekey">garcia-diaz-etal-2023-umuteam</identifier>
<identifier type="doi">10.18653/v1/2023.semeval-1.38</identifier>
<location>
<url>https://aclanthology.org/2023.semeval-1.38</url>
</location>
<part>
<date>2023-07</date>
<extent unit="page">
<start>285</start>
<end>292</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T UMUTeam at SemEval-2023 Task 12: Ensemble Learning of LLMs applied to Sentiment Analysis for Low-resource African Languages
%A García-Díaz, José Antonio
%A Caparros-laiz, Camilo
%A Almela, Ángela
%A Alcaráz-Mármol, Gema
%A Marín-Pérez, María José
%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
%X These working notes summarize the participation of the UMUTeam in the SemEval 2023 shared task: AfriSenti, focused on Sentiment Analysis in several African languages. Two subtasks are proposed, one in which each language is considered separately and another one in which all languages are merged. Our proposal to solve both subtasks is grounded on the combination of features extracted from several multilingual Large Language Models and a subset of language-independent linguistic features. Our best results are achieved with the African languages less represented in the training set: Xitsonga, a Mozambique dialect, with a weighted f1-score of 54.89\textbackslash%; Algerian Arabic, with a weighted f1-score of 68.52\textbackslash%; Swahili, with a weighted f1-score of 60.52\textbackslash%; and Twi, with a weighted f1-score of 71.14%.
%R 10.18653/v1/2023.semeval-1.38
%U https://aclanthology.org/2023.semeval-1.38
%U https://doi.org/10.18653/v1/2023.semeval-1.38
%P 285-292
Markdown (Informal)
[UMUTeam at SemEval-2023 Task 12: Ensemble Learning of LLMs applied to Sentiment Analysis for Low-resource African Languages](https://aclanthology.org/2023.semeval-1.38) (García-Díaz et al., SemEval 2023)
ACL