Enriching Digitized Medieval Manuscripts: Linking Image, Text and Lexical Knowledge

Abstract

This paper describes an on-going project of transcribing and annotating digitized manuscripts of medieval Spanish with paleographic and lexical information. We link lexical units from the manuscripts with the Multilingual Central Repository (MCR), making terms retrievable by any of the languages that integrate MCR. The goal of the project is twofold: creating a paleographic knowledge base from digitized medieval facsimiles, that will allow paleographers, philologist, historical linguist, and humanities scholars in general, to analyze and retrieve graphemic, lexical and textual information from historical documents; and on the other hand, developing machine readable documents that will link image representations of graphemic and lexical units in a facsimile with Linked Open Data resources. This paper concentrates on the encoding and cross-linking procedures. c 2015 Association for Computational Linguistics and The Asian Federation of Natural Language Processing.