Lectures on Language Technology and History

Uppsala, March 4, 2016

The computational linguistics group at Uppsala University is delighted to invite you to an afternoon of public lectures on language technology and history by leading experts in the field. The lectures will take place in Room 7-0043, English Park Campus, Uppsala University, on the 4th of March according to the schedule below. Attendance is free for anyone interested.

13.15-14.00 Michael Piotrowski
Leibniz Institute of European History
Digital Humanities, Computational Linguistics, and Natural Language Processing (slides)
I firmly believe that the digital humanities are more than digitizing sources, using digital research infrastructures and tools, and publishing research results online. Their real promise is not the acceleration of research by making it easier to access and analyze analyze larger corpora of sources. Rather, the point of the digital humanities is the introduction of formal modeling into humanities research; only this will actually advance scholarship and realize the full potential of computing in the humanities. There is thus a parallel to the role computational linguistics plays for linguistics. The digital humanities are furthermore connected to natural language processing—applied computational linguistics—through the use of NLP methods and tools in humanities research projects. In this talk, I will discuss some thoughts about the current state of the digital humanities and their relationship to computational linguistics and natural language processing.
14.00-14.45 Yvonne Adesam
Språkbanken
Department of Swedish
University of Gothenburg
Linguistic Annotation of Old Swedish Texts (slides)
The Swedish language of the Middle Ages, Old Swedish (13th to 16th century), is preserved in manuscripts, letters and early print. These documents are valuable for a wide variety of researchers, such as linguists interested in Swedish language changes during that time, law scholars who want to explore mediaeval laws, or theologians who study early translations of bible texts. Linguistic analysis can facilitate studies of this cultural heritage and enable new ways to explore it. However, apart from linguistic differences from contemporary Swedish in both lexicon, morphology, and syntax, the material poses challenges to the basis of traditional automatic tools for linguistic analysis. For example, the written language lacks standardization, resulting in e.g. numerous orthographic variants for one and the same word, and variation in marking sentence boundaries. In this talk, I present our work on exploring ways of handling these challenges, to create tools for automatic linguistic analysis of Old Swedish, with a particular focus on recent experiments on part-of-speech tagging of Old Swedish text.
14.45-15.15 Break
15.15-16.00 Mats Dahllöf
Department of Linguistics and Philology
Uppsala University
Finding Letters in Historical Manuscripts (slides)
The talk will propose an unsupervised and computationally efficient approach to the analysis of historical manuscripts. It will present a method for grouping handwriting elements into classes based on graphemic equivalence. The main purpose is letter extraction, but finding abbreviations, proper and accidental ligatures, letter components, and letter sequences is also valuable. The two main steps of the method are glyph segmentation and clustering. This method can be used to support cheap, but partial, manuscript transcription by giving a human annotator the opportunity to label the useful clusters and discard the remaining ones. The method could also be used to extract features for manuscript classification, e.g. in dating and scribe attribution, as well as to present data for qualitative palaeographic analysis.
16.00-16.45 Maria Ågren
Department of History
Uppsala University
Gender and Work in Early Modern Sweden: Approaches and Results (slides)