Automatic Text Processing for Historical Research

This article is devoted to the main possibilities of using natural language text processing technologies for historical research. The authors present a taxonomy of biographical facts and use text mining technologies (extraction of information from texts) to obtain biographical information from texts in Russian in accordance with the proposed types of biographical facts. The conducting of biographical research implies the need to view and study large amounts of textual information. The considerable part of the sources is currently presented in electronic form, which allows researchers to apply modern methods of extracting information to them. The article presents an overview of the main areas of application of technologies for automatic processing natural language texts in the humanities and describes the approach to the creation and implementation of the instrument for the extraction and systematization of biographical facts. This instrument will be useful to both historians and other users interested in biographical research.