Speaker: Tom Nicholls (Internet Institute, Oxford), Automated content classification with python's Natural Language Toolkit
About the network:
The goal of the HiCor network is to establish a work group of corpus linguists, computational linguists, and historians aiming at studying how annotated corpora can be built from historical documents, and used to mine historical texts and investigate cognitive phenomena. Although history and corpus linguistics share many of the same goals and methodological concerns, so far there has been little dialogue between the two disciplines. The goal of HiCor is to bridge this cross-disciplinary gap through the following activities: publications informing historians of the potential that corpus linguistics represents, creating a webpage for the network, and organizing a workshop.