@inproceedings{vivel-couso-etal-2026-meteogaleus,
title = "{M}eteo{G}al{E}us: An {I}berian Multilingual Weather Dataset in {G}alician, Euskera, and {S}panish",
author = "Vivel-Couso, Ainhoa and
Pramata, Nella Zabrina and
Robredo, David and
Soroa, Aitor and
Alonso-Moral, Jose Maria",
editor = "Piperidis, Stelios and
Bel, N{\'u}ria and
van den Heuvel, Henk and
Ide, Nancy and
Krek, Simon and
Toral, Antonio",
booktitle = "Proceedings of the Fifteenth Language Resources and Evaluation Conference",
month = may,
year = "2026",
address = "Palma de Mallorca, Spain",
publisher = "ELRA Language Resource Association",
url = "https://aclanthology.org/2026.lrec-1.777/",
doi = "10.63317/29v6u9pgo67x",
pages = "9905--9919",
abstract = "This paper introduces MeteoGalEus, a multilingual weather dataset that combines meteorological observations from two Spanish regional agencies, Euskalmet and MeteoGalicia. The dataset contains daily records spanning 4 years and 6 months, with aligned observations for both sources. MeteoGalEus captures key meteorological variables including temperature, wind and state of the sky. The dataset is provided in a structured format, facilitating data analysis and integration, with textual forecasts available in the official languages for each region (i.e., Galician and Spanish for MeteoGalicia; Euskera and Spanish for Euskalmet). By merging and harmonizing data from two regional agencies, MeteoGalEus is a unique resource for cross-regional weather analysis and multilingual climate studies. This dataset is suited for tasks requiring high-quality, aligned, and standardized weather data across multiple languages and regions. We conducted baseline experiments using LLaMA-based models in both zero-shot and fine-tuned settings to illustrate the use of MeteoGalEus for natural language generation (NLG). Fine-tuning led to consistent improvements across all metrics, with BERTScore increasing from 0.68 to 0.79, ROUGE from 0.20 to 0.35, and BLEU from 0.02 to 0.17 in the best-performing model. The experiments show how MeteoGalEus can be taken as a benchmark for multilingual and cross-regional NLG tasks."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="vivel-couso-etal-2026-meteogaleus">
<titleInfo>
<title>MeteoGalEus: An Iberian Multilingual Weather Dataset in Galician, Euskera, and Spanish</title>
</titleInfo>
<name type="personal">
<namePart type="given">Ainhoa</namePart>
<namePart type="family">Vivel-Couso</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Nella</namePart>
<namePart type="given">Zabrina</namePart>
<namePart type="family">Pramata</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">David</namePart>
<namePart type="family">Robredo</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Aitor</namePart>
<namePart type="family">Soroa</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jose</namePart>
<namePart type="given">Maria</namePart>
<namePart type="family">Alonso-Moral</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2026-05</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the Fifteenth Language Resources and Evaluation Conference</title>
</titleInfo>
<name type="personal">
<namePart type="given">Stelios</namePart>
<namePart type="family">Piperidis</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Núria</namePart>
<namePart type="family">Bel</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Henk</namePart>
<namePart type="family">van den Heuvel</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Nancy</namePart>
<namePart type="family">Ide</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Simon</namePart>
<namePart type="family">Krek</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Antonio</namePart>
<namePart type="family">Toral</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>ELRA Language Resource Association</publisher>
<place>
<placeTerm type="text">Palma de Mallorca, Spain</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>This paper introduces MeteoGalEus, a multilingual weather dataset that combines meteorological observations from two Spanish regional agencies, Euskalmet and MeteoGalicia. The dataset contains daily records spanning 4 years and 6 months, with aligned observations for both sources. MeteoGalEus captures key meteorological variables including temperature, wind and state of the sky. The dataset is provided in a structured format, facilitating data analysis and integration, with textual forecasts available in the official languages for each region (i.e., Galician and Spanish for MeteoGalicia; Euskera and Spanish for Euskalmet). By merging and harmonizing data from two regional agencies, MeteoGalEus is a unique resource for cross-regional weather analysis and multilingual climate studies. This dataset is suited for tasks requiring high-quality, aligned, and standardized weather data across multiple languages and regions. We conducted baseline experiments using LLaMA-based models in both zero-shot and fine-tuned settings to illustrate the use of MeteoGalEus for natural language generation (NLG). Fine-tuning led to consistent improvements across all metrics, with BERTScore increasing from 0.68 to 0.79, ROUGE from 0.20 to 0.35, and BLEU from 0.02 to 0.17 in the best-performing model. The experiments show how MeteoGalEus can be taken as a benchmark for multilingual and cross-regional NLG tasks.</abstract>
<identifier type="citekey">vivel-couso-etal-2026-meteogaleus</identifier>
<identifier type="doi">10.63317/29v6u9pgo67x</identifier>
<location>
<url>https://aclanthology.org/2026.lrec-1.777/</url>
</location>
<part>
<date>2026-05</date>
<extent unit="page">
<start>9905</start>
<end>9919</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T MeteoGalEus: An Iberian Multilingual Weather Dataset in Galician, Euskera, and Spanish
%A Vivel-Couso, Ainhoa
%A Pramata, Nella Zabrina
%A Robredo, David
%A Soroa, Aitor
%A Alonso-Moral, Jose Maria
%Y Piperidis, Stelios
%Y Bel, Núria
%Y van den Heuvel, Henk
%Y Ide, Nancy
%Y Krek, Simon
%Y Toral, Antonio
%S Proceedings of the Fifteenth Language Resources and Evaluation Conference
%D 2026
%8 May
%I ELRA Language Resource Association
%C Palma de Mallorca, Spain
%F vivel-couso-etal-2026-meteogaleus
%X This paper introduces MeteoGalEus, a multilingual weather dataset that combines meteorological observations from two Spanish regional agencies, Euskalmet and MeteoGalicia. The dataset contains daily records spanning 4 years and 6 months, with aligned observations for both sources. MeteoGalEus captures key meteorological variables including temperature, wind and state of the sky. The dataset is provided in a structured format, facilitating data analysis and integration, with textual forecasts available in the official languages for each region (i.e., Galician and Spanish for MeteoGalicia; Euskera and Spanish for Euskalmet). By merging and harmonizing data from two regional agencies, MeteoGalEus is a unique resource for cross-regional weather analysis and multilingual climate studies. This dataset is suited for tasks requiring high-quality, aligned, and standardized weather data across multiple languages and regions. We conducted baseline experiments using LLaMA-based models in both zero-shot and fine-tuned settings to illustrate the use of MeteoGalEus for natural language generation (NLG). Fine-tuning led to consistent improvements across all metrics, with BERTScore increasing from 0.68 to 0.79, ROUGE from 0.20 to 0.35, and BLEU from 0.02 to 0.17 in the best-performing model. The experiments show how MeteoGalEus can be taken as a benchmark for multilingual and cross-regional NLG tasks.
%R 10.63317/29v6u9pgo67x
%U https://aclanthology.org/2026.lrec-1.777/
%U https://doi.org/10.63317/29v6u9pgo67x
%P 9905-9919
Markdown (Informal)
[MeteoGalEus: An Iberian Multilingual Weather Dataset in Galician, Euskera, and Spanish](https://aclanthology.org/2026.lrec-1.777/) (Vivel-Couso et al., LREC 2026)
ACL