The Old Spanish Textual Archive, design and development of a corpus of medieval texts : lemmatization and pos tagging

This paper presents aspects related to the processing of forms, lemmas, grammatical analysis and texts in the Old Spanish Textual Archive (OSTA), a linguistic corpus of more than 32 million words, based on the more than 400 semipaleographic transcriptions of medieval texts written in Castilian, Asturian, Leonese, Navarro-Aragonese and Aragonese prepared by the collaborators of the Hispanic Seminary of Medieval Studies (HSMS). It also describes the process of tagging and lemmatization using Freeling, a Natural Language Processing tool, and HSMS-app, a textual analysis tool developed for this project.