Natural language processing and early-modern dirty data: applying IBM Languageware to the 1641 depositions

摘要

This article provides an account of the steps involved in adapting IBM's Languageware natural language processing software to a large corpus of highly non-standard 17th century documents. It examines the challenges encountered as part of this process, and outlines the approach adopted to provide a robust and reusable tool for the linguistic analysis of early modern source texts.