Chartex - White Paper

Researchers now have access to a deluge of data in the form of digitized historical records. One example is medieval charters, which record transfers of property and rights and are a major source for the study of people and places in the past, including the topography, economy and social relationships of pre-modern communities. Current digital search aids are not sufficiently sensitive to the needs of researchers seeking to exploit the wealth of textual detail within this data. To make effective use of it researchers need better computationally-based systems. The ChartEx Project aimed to research an innovative collection of computational methods to assist scholars in searching, analyzing, linking and thus understanding the content of charters. These methods could then be applied to other digitized texts, historical or contemporary. ChartEx research focussed in particular on the extraction of information from charters using a combination of natural language processing (NLP) and data mining (DM) to establish entities such as locations and related actors, events and dates. The third crucial component of the ChartEx Project was the use of novel instrumental interaction techniques to design a virtual workbench (VWB) that will allow researchers to both refine the processing of the NLP and DM, and to directly manipulate (visualise, confirm, correct, refine, augment, hypothesize) relationships extracted from the set of charters to gain new insights about the entities contained within them. The overall goals of the ChartEx Project were: 1. To develop and deploy a system that combines NLP and DM to extract data useful to researchers regarding locations and related actors, events and dates from digitised charters 2. To investigate whether researchers working with a virtual workbench based on novel instrumental interaction techniques will produce more useful knowledge from charters than a human working alone or an automated NLP/DM system working alone 3. To investigate whether the ChartEx system can produce efficient and accurate knowledge from charter documents by processing the information in English summaries of the charters in comparison to the full Latin text of the charters 4. To investigate whether the rules used with Latin charters of UK provenance can be applied to Latin charters from different parts of Europe, or if not, how much modification of the rules is needed in order to produce accurate relationships