The GRESEL-UNED project builds upon the CLARA-HD projects, where the Diary of Madrid was transcribed and annotated, and various technologies based on LLM were adapted for automatic text simplification. It also draws from projects like PhilPeriodicals, Minority Narratives, and DigiPhiLit, which involved the digitisation and transcription of historical Filipino newspapers using Transkribus. These materials, along with another literary corpus, were studied using methodologies from Digital Humanities and distant reading. For this occasion, we propose expanding the corpus to include newspapers from Spain and the Hispanic Caribbean published between 1877 and 1949. The yet-to-be-processed newspapers will be obtained from the National Library of Spain, where they are digitised.

The main objective is to develop new domain-specific resources and adapt existing linguistic tools and methodologies to extract relevant information from the corpus through vectorisation. The Humanists-UNED group, composed of national and international research personnel specialising in postcolonial literature and the study of historical press, will then formulate questions and construct a dictionary of significant terms categorised by domains according to the interests of potential users. Using the RAG methodology, our goal is to create resources for teaching and research that contribute to the study of postcolonial studies in Spanish. This entails examining the historical and cultural relations between Spain and the Philippines, Cuba, and Puerto Rico from 1877when national consciousness began and the territories of continental America gained independence until 1945, just after the end of World War II, at a time when these islands were still colonised by the United States.

Among the debates we aim to explore are the historical-cultural relationship of the territories of the Hispanic Caribbean and the Philippines with other Spanish-speaking countries, changes in the conception of Spanish colonialism, and the representation of women and debates on suffragism. In this regard, our intention is to gather information, recover, and highlight the role of women writers who were pioneering journalists and published their literary works in the pressworks that often were never published in book form.


Project members

  • Faculty of Philology, National University of Distance Education (UNED)
  • School of Computer Science, National University of Distance Education (UNED)

Team members

Acknowledgements

The project is funded through a Spanish State Subprogram for Knowledge Generation 2023 under grant agreement No. PID2023-151280OB-C22.