期刊名称：Conference on European Chapter of the Association for Computational Linguistics (EACL)
出版年度：2017
卷号：2017
页码：1138-1149
语种：English
出版社：ACL Anthology
摘要：Authorship attribution is associated with important applications in forensics and humanities research. A crucial point in this field is to quantify the personal style of writing, ideally in a way that is not affected by changes in topic or genre. In this paper, we present a novel method that enhances authorship attribution effectiveness by introducing a text distortion step before extracting stylometric measures. The proposed method attempts to mask topic-specific information that is not related to the personal style of authors. Based on experiments on two main tasks in authorship attribution, closed-set attribution and authorship verification, we demonstrate that the proposed approach can enhance existing methods especially under cross-topic conditions, where the training and test corpora do not match in topic.
