On the Problem of Automatically Aligning Indicators to SDGs
![Thumbnail](/xmlui/bitstream/handle/10234/207341/ESWC_2023_Poster.pdf.jpg?sequence=4&isAllowed=y)
View/ Open
Impact
![Google Scholar](/xmlui/themes/Mirage2/images/uji/logo_google.png)
![Microsoft Academico](/xmlui/themes/Mirage2/images/uji/logo_microsoft.png)
Metadata
Show full item recordcomunitat-uji-handle:10234/9
comunitat-uji-handle2:10234/7038
comunitat-uji-handle3:10234/159830
comunitat-uji-handle4:
INVESTIGACIONMetadata
Title
On the Problem of Automatically Aligning Indicators to SDGsDate
2023-10-21Publisher
Springer NatureBibliographic citation
Soriano, M., Berlanga, R., Lanza-Cruz, I. (2023). On the Problem of Automatically Aligning Indicators to SDGs. In: Pesquita, C., et al. The Semantic Web: ESWC 2023 Satellite Events. ESWC 2023. Lecture Notes in Computer Science, vol 13998. Springer, Cham. https://doi.org/10.1007/978-3-031-43458-7_26Type
info:eu-repo/semantics/conferenceObjectVersion
info:eu-repo/semantics/submittedVersionSubject
Abstract
In this paper we present a first approach to the application of transformer-based language models to the automatic alignment to sustainable development goals (SDGs). This task is quite relevant for the development of ... [+]
In this paper we present a first approach to the application of transformer-based language models to the automatic alignment to sustainable development goals (SDGs). This task is quite relevant for the development of new tools that aim at measuring the engagement degree of the organization’s indicators to the SGDs. Our first experiments show that this task is hard, and that even powerful large language models do not achieve a high accuracy as in other NLP tasks. [-]
Description
Ponencia presentada en The Semantic Web: ESWC 2023 Satellite Events , Hersonissos, Crete, Greece, May 28 - June 1, 2023.
Is part of
Lecture Notes in Computer Science ((LNCS,volume 13998))Funder Name
Spanish Ministry of Science, Innovation and Universities | Generalitat Valenciana
Project code
PDC2021-121097 | INVEST/2022/308
Project title or grant
INVESTIGO