Search

This paper discusses best practices for sharing and reusing Ground Truth in Handwritten Text Recognition infrastructures, as well as ways to reference and acknowledge contributions to the creation and enrichment of data within these systems. We discuss how one can place Ground Truth data in a repository and, subsequently, inform others through HTR-United. Furthermore, we want to we want to suggest appropriate citation methods for HTR data, models, and contributions made by volunteers. Moreover, when using digitised sources (digital facsimiles), it becomes increasingly important to distinguish between the physical object and the digital collection. These topics all relate to the proper acknowledgement of labour put into digitising, transcribing, and sharing Ground Truth HTR data. This also points to broader issues surrounding the use of machine learning in archival and library contexts, and how the community should begin to acknowledge and record both contributions and data provenance.

It is assumed, in palaeography, papyrology and epigraphy, that a certain amount of uncertainty is inherent in the reading of damaged and abraded texts. Yet we have not really grappled with the fact that, nowadays, as many scholars tend to deal with digital images of texts, rather than handling the texts themselves, the procedures for creating digital images of texts can insert further uncertainty into the representation of the text created. Technical distortions can lead to the unintentional introduction of ‘artefacts’ into images, which can have an effect on the resulting representation. If we cannot trust our digital surrogates of texts, can we trust the readings from them? How do scholars acknowledge the quality of digitised images of texts? Furthermore, this leads us to the type of discussions of representation that have been present in Classical texts since Plato: digitisation can be considered as an alternative form of representation, bringing to the modern debate of the use of digital technology in Classics the familiar theories of mimesis (imitation) and ekphrasis (description): the conversion of visual evidence into explicit descriptions of that information, stored in computer files in distinct linguistic terms, with all the difficulties of conversion understood in the ekphratic process. The community has not yet considered what becoming dependent on digital texts means for the field, both in practical and theoretical terms. Issues of quality, copying, representation, and substance should be part of our dialogue when we consult digital surrogates of documentary material, yet we are just constructing understandings of what it means to rely on virtual representations of artefacts. It is necessary to relate our understandings of uncertainty in palaeography and epigraphy to our understanding of the mechanics of visualization employed by digital imaging techniques, if we are to fully understand the impact that these will have.

The ink and stylus tablets discovered at the Roman Fort of Vindolanda have provided a unique resource for scholars of ancient history. However, the stylus tablets in particular have proved extremely difficult to read. The aim of this thesis is to explore the extent to which techniques from Artificial Intelligence can be used to develop a system that could aid historians in reading the stylus texts. This system would utilise image processing techniques that have been developed in Engineering Science to analyse the stylus tablets, whilst incorporating knowledge elicited from experts working on the texts, to propagate possible suggestions of the text contained within the tablets. This thesis reports on what appears to be the first system developed to aid experts in the process of reading an ancient document. There has been little previous research carried out to see how papyrologists actually carry out their task. This thesis studies closely how experts working with primary sources, such as the Vindolanda Texts, operate. Using Knowledge Elicitation Techniques, a model is proposed for how they read a text. Information regarding the letter forms and language used at Vindolanda is collated, A corpus of annotated images is built up, to provide a data set regarding the letter forms used in the ink and stylus texts. In order to relate this information to the work done on image processing, a stochastic Minimum Description Length (MDL) architecture is adopted, and adapted, to form the basis of a system that can propagate interpretations of the Vindolanda texts. In doing so a system is constructed that can read in image data and output textual interpretations of the writing that appears on the documents. It is demonstrated that knowledge elicitation techniques can be used to capture and mobilise expert information. The process of reading ancient, and ambiguous texts, is made explicit. It is also shown that MDL can be used as a basis to build large systems that reason about complex information effectively. This research presents the first stages towards developing a cognitive visual system that can propagate realistic interpretations from image data, and so aid the papyrologists in their task.