Developing a Pipeline for Automatic Linguistic Analysis of Historical Manuscripts and Early Printings: The Pre-Modern Slavic Case

We report on experiments with Handwritten Text Recognition models to automatically create large pre-modern Slavic text corpora and to use these corpora without manual post-correction (as raw data and with uncorrected POS tags) for quantitative linguistic analysis (inferential statistics, stylometry); we evaluate the actual noise in the data.

Related Organizations

University of Kragujevac
Serbia
University of Freiburg
Germany
Université Freiburg
Germany
Bavarian Academy of Sciences and Humanities
Germany

Keywords

Paper, attribution studies and stylometric analysis, Handwritten Text Recognition, full morphology tagging, representation, optical character recognition and handwriting recognition, Linguistics, pre-modern Slavic, manuscripts description, Short Presentation, statistical analysis, stylometry, FOS: Languages and literature, and analysis, natural language processing

Impact byBIP!

	selected citations These citations are derived from selected sources. This is an alternative to the "Influence" indicator, which also reflects the overall/total impact of an article in the research community at large, based on the underlying citation network (diachronically).	0
	popularity This indicator reflects the "current" impact/attention (the "hype") of an article in the research community at large, based on the underlying citation network.	Average
	influence This indicator reflects the overall/total impact of an article in the research community at large, based on the underlying citation network (diachronically).	Average
	impulse This indicator reflects the initial momentum of an article directly after its publication, based on the underlying citation network.	Average