News and announcements
Paper overview July 08, 2026
Historical document transcription remains challenging due to complex layouts, diverse writing styles, and the presence of obsolete characters and abbreviations. Our recently published paper, “FP-THD: Full page transcription of historical documents”, presents an end-to-end pipeline designed for automatic full-page transcription.
Paper overview July 07, 2026
In crowdsourcing, dividing work into narrowly defined microtasks may affect the quality of the final product. Our study, published in Transactions in GIS and in collaboration with researchers from the University of Camerino, examines this problem in the context of humanitarian mapping initiatives coordinated using the Humanitarian OpenStreetMap Team Tasking Manager, analyzing 4619 projects and over 1.4 million microtasks.
Paper overview July 06, 2026
A fundamental challenge in digital product design is ensuring that actual mental models of users align with the intended functionality of the system. When discrepancies arise, usability can suffer, leading to inefficient interactions and reduced adoption. Usability testing lets development teams identify design problems in digital products by collecting qualitative and quantitative information. However, this technique is often not able to provide a panoramic view of the interaction with the system, especially when dealing with complex interfaces such as those used in geospatial search engines and we need to analyse the quantitative data compiled during testing.
Paper overview July 05, 2026
Governmental policies for transparency and reuse of public sector information have encouraged the launch of open government data portals around the world. Many of these portals are based on pyramidal structures: national open data portals are aggregators of the contents harvested from open data portals maintained by governments in charge of administrative areas with a narrower scope. Taking into account this hierarchical organization, these open data portals lack consistent and scalable mechanisms for thematic annotation, limiting dataset discoverability.
Paper overview June 23, 2026
Los modelos de lenguaje grandes (Large Language Models, LLM) permiten interactuar con sistemas digitales mediante lenguaje natural. Sin embargo, la mayoría de las soluciones actuales dependen de infraestructuras en la nube, algo que puede resultar problemático durante el trabajo agrícola en zonas con conectividad limitada.