Jump to ContentJump to Main Navigation
Image to InterpretationAn Intelligent System to Aid Historians in Reading the Vindolanda Texts$
Users without a subscription are not able to see the full content.

Melissa Terras

Print publication date: 2006

Print ISBN-13: 9780199204557

Published to Oxford Scholarship Online: September 2007

DOI: 10.1093/acprof:oso/9780199204557.001.0001

Show Summary Details
Page of

PRINTED FROM OXFORD SCHOLARSHIP ONLINE (oxford.universitypressscholarship.com). (c) Copyright Oxford University Press, 2021. All Rights Reserved. An individual user may print out a PDF of a single chapter of a monograph in OSO for personal use. date: 24 September 2021

Using Artificial Intelligence to Read the Vindolanda Texts

Using Artificial Intelligence to Read the Vindolanda Texts

(p.123) 4 Using Artificial Intelligence to Read the Vindolanda Texts
Image to Interpretation

Melissa M. Terras (Contributor Webpage)

Dr Paul Robertson

Oxford University Press

This chapter describes the implementation of the artificial intelligence system which was developed to read the Vindolanda texts. An appropriate architecture, the GRAVA system (originally developed for aerial image understanding) was identified, adopted, and adapted for this research. Due to the diverse nature of this text’s audience, this chapter provides an overview of the system for the less computer oriented reader; Appendix A describes the technicalities and mathematical underpinnings of the system in detail. Readers without a background in computing or engineering science should find this chapter sufficient to explain the workings of the computer system. The system in question, GRAVA, allows small modules or computer ‘agents’ to work together to compare and contrast different types of information. It does this using Minimum Description Length. The GRAVA system is introduced, and the application of the system to the data gathered from the Vindolanda texts is demonstrated. It is then explained how and why the GRAVA system had to be adapted to deal with the complexity of the Vindolanda texts, and the basic underlying structure of the system is discussed.

Keywords:   agents, agent based architecture, Minimum Description Length, system architecture

Oxford Scholarship Online requires a subscription or purchase to access the full text of books within the service. Public users can however freely search the site and view the abstracts and keywords for each book and chapter.

Please, subscribe or login to access full text content.

If you think you should have access to this title, please contact your librarian.

To troubleshoot, please check our FAQs , and if you can't find the answer there, please contact us .