Sarah Rees Jones (University of York), Roger Evans (University of Brighton); Robin Sutherland-Harris (University of Toronto); Stefania Merlo Perring (University of York); Helen Petrie (University of York); Christopher Power (University of York).
The ChartEx Project is funded under the Digging into Data Challenge 2012-13 (www.diggingintodata.org).
The project is using both natural language processing and data mining techniques to establish entities such as sites (site in this context refers to a specific location or piece of land) and actors and events related to those sites. The project is also developing a virtual workbench to support historians in working with large corpora of digital charters and the vast amounts of information that can now be extracted from them.
Our session will be divided into four short papers which together will provide an overview of our progress to date.
Title: The ChartEx Challenge
Presenter: Dr S. Rees Jones (York)
This paper will introduce the purpose and scope of the research using examples rooted in historical practice relating to research in both urban and rural medieval landscapes. It will provide an overview of the charters used in ChartEx, which range in date from the tenth to the sixteenth century and originate from both England and northern France. It will address the strengths and weaknesses of these collections within the project, deriving both from the original diplomatic of the different charter series themselves and their conversion into digital resources in both English and Latin.
Title: People, places and events in charters: exploring the language of charters within ChartEx.
Co-presenters: Robin Sutherland-Harris (Toronto) and Dr Roger Evans (Brighton)
This paper will provide an overview of the collaborative work between historians and linguists in developing an annotations schema for use in developing natural language processing (NLP) of digital charter texts. It will also present some of the results of preliminary analysis of individual digital charter texts using NLP.
Title: Reconstructing spatial relationships from charters: a collaboration between Data Mining and Historical Topography.
Presenter: Dr Stefania Merlo Perring (York)
This paper will address the process and the results of the collaborative research between historians and experts in data mining (DM). DM is used to establish relationships between people/actors, sites and events in large sets of charters using probabilistic reasoning.
Title: Developing a virtual workbench for charter historians
Co-presenters: Professor Helen Petrie (York) and Dr Christopher Power (York)
This paper will address the process of designing a prototype workbench for historians in searching, retrieving and visualising entities and relationship from charter sets. The workbench also supports further reasoning allowing historians to validate relationships proposed by the NLP and DM, to identify new entities and to create new relationships (for example between people and sites) without compromising the integrity of the original data.