EBG
收藏arXiv2025-09-30 收录
官方服务：
资源简介：
该数据集名为扩展的布伦南-格林斯坦特语料库，包含了45位个体的写作样本。这些个体被要求上传自己的写作示例，并在尝试掩饰自己写作风格的情况下撰写一篇短文。该语料库被用于评估模型在作者试图隐藏自己的写作特征时，识别出作者的能力。所涉及的任务是作者身份验证。
This dataset, named the Extended Brennan-Greenstein Corpus, contains writing samples from 45 individuals. These individuals were asked to upload their own writing samples and compose a short essay while attempting to disguise their writing styles. This corpus is used to evaluate a model's ability to identify authors when the authors attempt to conceal their writing characteristics. The task involved is authorship verification.
提供机构：
Brennan et al.
