Marianne Ritsema van Eck - ‘The Legal Transactions in the Acts of the Leuven Alderman’s Rolls 1421:

afstudeercolloquium

‘The Legal Transactions in the Acts of the Leuven Alderman’s Rolls 1421: Towards a Formal Semantic Model of the Act’ The medieval manuscript of the Leuven Alderman’s Rolls of 1421 is a hard nut to crack. This text is included in the project ‘Monk’ with the aim of achieving Optical Character Recognition for the current Gothic minuscule it is written in. Indeed, the step from pixel to meaning is a very difficult one to take. Even when one can read the text on the manuscript page – a hard task for Monk as well as human annotators - this does not automatically lead to understanding. To get at the semantics enclosed in the digital image of the manuscript page several translations are needed: trough time, of language, and man-machine. During this highly interdisciplinary project the accomplishments of historical philological method and manuscript studies were put into practice to create a ‘world model’ for this text. Using the resulting framework for understanding the manuscript, a formal semantic model was constructed for the legal acts it contains. This model may in time be worked out in Web Ontology Language (OWL) to aid Monk in analysing the manuscript on a higher semantic level than the textual one alone. An important fact to note is that the use of the XML Schema ALTO was not aspired to; due to the erratic nature of the page layout and lining in this manuscript a system of polygonal visual regions connected to the semantic model by unique identifier codes will be proposed.