- Add
corpus/toPan20.py
to convert the dataset to the new PAN 2020 format.
Continuing original README:
Bevendorff, Stein, Hagen, Potthast; 2019; Generalizing Unmasking for Short Texts
This repository contains the raw experiment data from the paper and our new authorship corpus.
The unmasking framework can be found in our unmasking repository.