@inproceedings{macias-etal-2024-scaling,
title = "Scaling Sustainable Development Goal Predictions across Languages: From {E}nglish to {F}innish",
author = {Macias, Melany and
Kharlashkin,, Lev and
Huovinen, Leo and
H{\"a}m{\"a}l{\"a}inen, Mika},
editor = {H{\"a}m{\"a}l{\"a}inen, Mika and
Pirinen, Flammie and
Macias, Melany and
Crespo Avila, Mario},
booktitle = "Proceedings of the 9th International Workshop on Computational Linguistics for Uralic Languages",
month = nov,
year = "2024",
address = "Helsinki, Finland",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2024.iwclul-1.17",
pages = "132--137",
abstract = "In this paper, we leverage an exclusive English dataset to train diverse multilingual classifiers, investigating their efficacy in adapting to Finnish data. We employ an exclusively English classification dataset of UN Sustainable Development Goals (SDG) in an education context, to train various multilingual classifiers and examine how well these models can adapt to recognizing the same classes within Finnish university course descriptions. It{'}s worth noting that Finnish, with a mere 5 million native speakers, presents a significantly less-resourced linguistic context compared to English. The best performing model in our experiments was mBART with an F1-score of 0.843.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="macias-etal-2024-scaling">
<titleInfo>
<title>Scaling Sustainable Development Goal Predictions across Languages: From English to Finnish</title>
</titleInfo>
<name type="personal">
<namePart type="given">Melany</namePart>
<namePart type="family">Macias</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Lev</namePart>
<namePart type="family">Kharlashkin,</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Leo</namePart>
<namePart type="family">Huovinen</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Mika</namePart>
<namePart type="family">Hämäläinen</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2024-11</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 9th International Workshop on Computational Linguistics for Uralic Languages</title>
</titleInfo>
<name type="personal">
<namePart type="given">Mika</namePart>
<namePart type="family">Hämäläinen</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Flammie</namePart>
<namePart type="family">Pirinen</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Melany</namePart>
<namePart type="family">Macias</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Mario</namePart>
<namePart type="family">Crespo Avila</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Helsinki, Finland</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>In this paper, we leverage an exclusive English dataset to train diverse multilingual classifiers, investigating their efficacy in adapting to Finnish data. We employ an exclusively English classification dataset of UN Sustainable Development Goals (SDG) in an education context, to train various multilingual classifiers and examine how well these models can adapt to recognizing the same classes within Finnish university course descriptions. It’s worth noting that Finnish, with a mere 5 million native speakers, presents a significantly less-resourced linguistic context compared to English. The best performing model in our experiments was mBART with an F1-score of 0.843.</abstract>
<identifier type="citekey">macias-etal-2024-scaling</identifier>
<location>
<url>https://aclanthology.org/2024.iwclul-1.17</url>
</location>
<part>
<date>2024-11</date>
<extent unit="page">
<start>132</start>
<end>137</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Scaling Sustainable Development Goal Predictions across Languages: From English to Finnish
%A Macias, Melany
%A Kharlashkin,, Lev
%A Huovinen, Leo
%A Hämäläinen, Mika
%Y Hämäläinen, Mika
%Y Pirinen, Flammie
%Y Macias, Melany
%Y Crespo Avila, Mario
%S Proceedings of the 9th International Workshop on Computational Linguistics for Uralic Languages
%D 2024
%8 November
%I Association for Computational Linguistics
%C Helsinki, Finland
%F macias-etal-2024-scaling
%X In this paper, we leverage an exclusive English dataset to train diverse multilingual classifiers, investigating their efficacy in adapting to Finnish data. We employ an exclusively English classification dataset of UN Sustainable Development Goals (SDG) in an education context, to train various multilingual classifiers and examine how well these models can adapt to recognizing the same classes within Finnish university course descriptions. It’s worth noting that Finnish, with a mere 5 million native speakers, presents a significantly less-resourced linguistic context compared to English. The best performing model in our experiments was mBART with an F1-score of 0.843.
%U https://aclanthology.org/2024.iwclul-1.17
%P 132-137
Markdown (Informal)
[Scaling Sustainable Development Goal Predictions across Languages: From English to Finnish](https://aclanthology.org/2024.iwclul-1.17) (Macias et al., IWCLUL 2024)
ACL