CCTAA: A Reproducible Corpus for Chinese Authorship Attribution Research
Proceedings of the Thirteenth International Conference on Language Resources and Evaluation (LREC 2022)
Abstract
Authorship attribution infers the likely author of an unsigned, single-authored document from a pool of candidates. Despite recent advances, a lack of standard, reproducible testbeds for Chinese language documents impedes progress. In this paper, we present the Chinese Cross-Topic Authorship Attribution (CCTAA) corpus. It is the first standard testbed for authorship attribution on contemporary Chinese prose. The cross-topic design and relatively inflexible genre of newswire contribute to an appropriate level of difficulty. It supports reproducible research by using pre-defined data splits. We show that a sequence classifier based on pre-trained Chinese RoBERTa embedding and a support vector machine classifier using function character n-gram frequency features perform below expectations on this task. The code for generating the corpus and reproducing the baselines is freely available at https://codeberg.org/haining/cctaa.