5 documents found, page 1 of 1
Assessing European and Brazilian Portuguese LLMs for NER in Specialised Domains
Nunes, Rafael Oleques; Santos, Joaquim; Spritzer, André; Balreira, Dennis G.; Freitas, Carla M. Dal Sasso; Olival, Fernanda; Cameron, Helena FreireThis paper discusses the impact of Portuguese variants in Large Language Models for the task of named entity recognition (NER) in specialised domains. The tests were made on a Brazilian Portuguese le gal and a European Portuguese historical corpora. The models taken into account are BERTimbau (PT-BR), Albertina (PT-PT and PT-BR), and XML-R (multilingual). The impact was more evident in the Portuguese historical...
From the text sources to the map: the Parish Memories, a para cadastre of Portu...
Ribeiro, Ana Sofia; Olival, Fernanda; Cameron, Helena Freire; Vieira, Renata; Farrica, FátimaThis study explores the cartographic reconstruction of 18th-century Portuguese parishes and municipalities, using Vila Viçosa as a case study. Based on the 1758 Parish Memories and other historical sources, it employs Natural Language Processing and QGIS to extract and map geographical and administrative data. The research highlights challenges such as overlapping or vanished parishes, particularly in rural are...
As Memórias Paroquiais: do manuscrito ao digital
Olival, Fernanda; Cameron, Helena Freire; Vieira, RenataThis text aims to trace the history of the custody of the Parish Memories ("Memórias Paroquiais"), from the diffusion of the surveys in 1758, to the current projects which aim at their conversion into digital objects and data. Reflecting on this itineracio is also a way to evaluate and rethink working strategies on this collection. It should be noted that this is a relevant resource for the understanding of mid...
Planear a normalização automática: tipologia de variação gráfica do corpus das ...
Cameron, Helena Freire; Olival, Fernanda; Vieira, RenataDigital Humanities are now essential for studies on large-scale textual corpora, where the transformation of text into processable data regarding linguistic phenomena requires a multidisciplinary treatment. In this article we will present an approach in Digital Humanities, which was applied to a Portuguese textual corpus from the 18th-century, gathered from a set of documents known as Memórias Paroquiais [“The ...
As Memórias Paroquiais (1758) do atual concelho de Vila Viçosa
Olival, Fernanda; Cameron, Helena Freire; Farrica, Fátima; Vieira, RenataThe article has three aims: to make the texts of the Memórias Paroquiais known, publishing them with modernised spelling but without changes in to the punctuation; to study the profile of the priests who wrote the answers to this survey of 1758; and to identify some of the specificities of the municipality of Vila Viçosa, based on the reading of the territory presented by its parish priests. We concluded that t...