The Topic Confusion Task: A Novel Evaluation
Scenario for Authorship Attribution
M. Altakrori, J. C. K. Cheung, and B. C. M. Fung. Topic Confusion Task: A Novel Evaluation Scenario for Authorship Attribution. Findings of the 2021 Conference on Empirical Methods in Natural Language Processing (EMNLP), pages 4242-4256, Punta Cana, Dominican Republic: ACL, November 2021.
Here's the code for this paper .
[x] The cross-topic extended Guardian collection. We used this dataset for authorship attribution and the Topic Confusion task.
[x] BNC (For the masking approach). We used the frequency list (Filename: all.num.gz) for the Masking approach.