The papers in this volume are presented at the Workshop on Processing Historical Language, held in conjunction with the 40-year anniversary of NoDaLiDa, 22 May 2017 in Gothenburg.
While historical texts have long attracted interest from language historians and historical linguists, we have seen an increased attention to the problems particular to processing historical data from a computational perspective in the last decade or so. ‘Processing’ here entails a wide range of text processing tasks, such as creating electronic transcriptions and editions of manuscripts, constructing lexica, tagging, and parsing, as well as contentoriented processing such as semantic parsing and information extraction. The aim of the workshop is to bring together researchers working on processing historical materials with a particular focus on work that investigates the combination of datadriven and knowledge-driven modelling.
We received 16 submissions, which were each reviewed (double blind) by three programme committee members. Because of the amount and quality of the submissions, the workshop, initially planned as a half-day workshop, was prolonged to accommodate 9 oral presentations.
The authors come from eight different European countries. The research presented at the workshop covers a range of topics related to historical materials, including spelling standardization, linguistic analysis, identification of text re-use, and data visualization. Featured languages are Dutch, English, Finnish, German, Icelandic, Latin, and Spanish, at varying historical stages. The programme also includes an invited talk by Stefanie Dipper, titled Variance in historical data: how bad is it and how can we profit from it for historical linguistics?
We are excited to have such a varied and inspiring programme and would like to thank the invited speaker, authors, and reviewers for their valuable contributions.
May 1, 2017
Gerlof Bouma and Yvonne Adesam
The workshop is organized as part of project MAÞiR – Methods for the automatic Analysis of Text in digital Historical Resources – funded by Marcus and Amalia Wallenberg Foundation, grant MAW 2012.0146.