Requirements Classification Using FastText and BETO in Spanish Documents

UDC.coleccionInvestigación
UDC.conferenceTitleREFSQ 2023
UDC.departamentoCiencias da Computación e Tecnoloxías da Información
UDC.endPage176
UDC.grupoInvLaboratorio de Bases de Datos (LBD)
UDC.institutoCentroCITIC - Centro de Investigación de Tecnoloxías da Información e da Comunicación
UDC.startPage159
UDC.volume13975
dc.contributor.authorLimaylla-Lunarejo, María-Isabel
dc.contributor.authorCondori Fernández, Nelly
dc.contributor.authorRodríguez Luaces, Miguel
dc.date.accessioned2026-10-19T09:55:57Z
dc.date.available2026-10-19T09:55:57Z
dc.date.issued2023
dc.descriptionPresented at: 29th International Working Conference on Requirements Engineering: Foundation for Software Quality (REFSQ 2023), April 17–20, 2023, Barcelona, Spain. This version of the article has been accepted for publication, after peer review and is subject to Springer Nature’s AM terms of use, but is not the Version of Record and does not reflect post-acceptance improvements, or any corrections. The Version of Record is available online at: https://doi.org/10.1007/978-3-031-29786-1_11 Code and datasets used: https://zenodo.org/records/7311148
dc.description.abstract[Abstract] Context and motivation: Machine Learning (ML) algorithms and Natural Language Processing (NLP) techniques have effectively supported the automatic software requirements classification. The emergence of pre-trained language models, like BERT, provides promising results in several downstream NLP tasks, such as text classification. Question/problem: Most ML/DL approaches on requirements classification show a lack of analysis for requirements written in the Spanish language. Moreover, there has not been much research on pre-trained language models, like fastText and BETO (BERT for the Spanish language), neither in the validation of the generalization of the models. Principal ideas/results: We aim to investigate the classification performance and generalization of fastText and BETO classifiers in comparison with other ML/DL algorithms. The findings show that Shallow ML algorithms outperformed fastText and BETO when training and testing in the same dataset, but BETO outperformed other classifiers on prediction performance in a dataset with different origins. Contribution: Our evaluation provides a quantitative analysis of the classification performance of fastTest and BETO in comparison with ML/DL algorithms, the external validity of trained models on another Spanish dataset, and the translation of the PROMISE NFR dataset in Spanish.
dc.description.sponsorshipThis research was partially funded by Xunta de Galicia/FEDER-UE ED413C 2021/53 (Database Lab, UDC) and Galician Ministry of Culture, Education, Professional Training, and University (grants ED431G2019/04, ED431C2022/19).
dc.description.sponsorshipXunta de Galicia; ED413C 2021/53
dc.description.sponsorshipXunta de Galicia; ED431G 2019/04
dc.description.sponsorshipXunta de Galicia; ED431C 2022/19
dc.description.urihttps://doi.org/10.5281/zenodo.7311148
dc.identifier.citationLimaylla-Lunarejo, MI., Condori-Fernandez, N., Luaces, M.R. (2023). Requirements Classification Using FastText and BETO in Spanish Documents. In: Ferrari, A., Penzenstadler, B. (eds) Requirements Engineering: Foundation for Software Quality. REFSQ 2023. Lecture Notes in Computer Science, vol 13975, pp. 59–176. Springer, Cham. https://doi.org/10.1007/978-3-031-29786-1_11
dc.identifier.doi10.1007/978-3-031-29786-1_11
dc.identifier.isbn978-3-031-29786-1
dc.identifier.urihttps://hdl.handle.net/2183/49829
dc.language.isoeng
dc.publisherSpringer Nature
dc.relation.isbasedonCode and datasets used
dc.relation.urihttps://doi.org/10.1007/978-3-031-29786-1_11
dc.rights© 2023 The Author(s), under exclusive license to Springer Nature Switzerland AG
dc.rights.accessRightsopen access
dc.subjectSpanish requirements
dc.subjectAutomatic classification requirements
dc.subjectFastText
dc.subjectBETO
dc.titleRequirements Classification Using FastText and BETO in Spanish Documents
dc.typeconference output
dspace.entity.typePublication
relation.isAuthorOfPublicationfbde3bd9-d786-4ef0-89ec-6af2091fa415
relation.isAuthorOfPublication.latestForDiscoveryfbde3bd9-d786-4ef0-89ec-6af2091fa415

Files

Original bundle

Now showing 1 - 1 of 1
Loading...
Thumbnail Image
Name:
RodriguezLuaces_Miguel_2023_Requirements_Classification_Using_FastText_and_BETO.pdf
Size:
363.55 KB
Format:
Adobe Portable Document Format