Dr. Paul Dijstelberge will present Metabotnik. Metabotnik allows scholars to gather a selection of high-resolution image files, add metadata and contextual information, and render a Seadragon compatible gigapixel image ready for use, all while doing so from a web-based tool.
Dieuwke Hupkes will discuss part-of-speech tagging of 17th century Dutch. If one wants to extract information from a (historical) text, it is often useful to know the grammatical category (or part-of-speech tag) of all words in that text. Tools that automatically assign high accuracy such tags to modern Dutch text are freely available, but these tools do not exist for 17th century Dutch. Dieuwke will present an evaluation of the performance of modern Dutch taggers when used on historical Dutch data and several methods to improve the tagging accuracy.
Rosa Merino Claros introduces her project on extraction and exploration of spatial information in (historical) documents. She aims to build a tool that performs a geographical search along a text document and is capable of recognizing, disambiguating and visualizing any place entity such as countries, regions, cities, neighbourhoods, streets or even buildings, showing a map with all the locations named in text as final output.
When? Thursday 27 November, 3-5 pm. Where? Vondelzaal (University Library, Singel 425).