Literary and Linguistic Computing Advance Access originally published online on February 22, 2005
Literary and Linguistic Computing 2005 20(1):41-59; doi:10.1093/llc/fqh042
| ||||||||||||||||||||||||||||||||||||||||||||||||
Articles |
Reading the Readers: Modelling Complex Humanities Processes to Build Cognitive Systems
University College London, UK
Melissa Terras, School of Library, Archive and Information Studies, Henry Morley Building, University College London, Gower Street, London WC1E 6BT, UK. E-mail: m.terras{at}ucl.ac.uk
The ink and stylus tablets discovered at the Roman Fort of Vindolanda are a unique resource for scholars of ancient history. However, the stylus tablets have proved particularly difficult to read. This paper describes the initial stages in the development of a computer system designed to aid historians in the reading of the stylus tablets. A detailed investigation was undertaken, using Knowledge Elicitation techniques borrowed from Artificial Intelligence, Cognitive Psychology, and Computational Linguistics, to elicit the processes experts use whilst reading an ancient text. The resulting model was used as the basis of a computer architecture to construct a system which takes in images of the tablets and outputs plausible interpretations of the documents. It is demonstrated that using Knowledge Elicitation techniques can further the understanding of complex processes in the humanities, and that these techniques can provide an underlying structure for the basis of a computer system that replicates that process. As such it provides significant insight into how experts work in the humanities, whilst providing the means to develop tools to assist them in their complex task.