Authorship Attribution for Neural Text Generation
Clean_Generated folder contains jupyter notebooks of classical machine learning models used to build baseline for classifying the datasets. The notebooks are named accordingly. Next, there are two folders in Clean_Generated, stylistic and single. Stylistic contains the classification models for the linguistic features and Single contains the notebook for the Turing Test problem (human vs. machine).
In the data folder you will find the generated articles of the 8 text-generators + human-written articles. All the datasets for the different problem settings are in there except for the P1 dataset. The code for the generating the P1 dataset can be found HERE since it is too heavy to put in github.
Citation
@inproceedings{uchendu2020authorship,
title={Authorship Attribution for Neural Text Generation},
author={Uchendu, Adaku and Le, Thai and Shu, Kai and Lee, Dongwon},
booktitle={Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing (EMNLP)},
pages={8384--8395},
year={2020}
}