Towards Robust and Privacy-preserving Text Representations

• DOI: 10.18653/v1/p18-2005
• Publication Date: 2019-06-29T19:52:10Z
• Authors: Yitong Li; Timothy Baldwin; Trevor Cohn
• Keywords: FOS: Computer and information sciences; Computer Science - Computation and Language; 0202 electrical engineering, electronic engineering, information engineering; 02 engineering and technology; Computation and Language (cs.CL)

Accepted to ACL 2018<br/>Written text often provides sufficient clues to identify the author, their gender, age, and other important attributes. Consequently, the authorship of training and evaluation corpora can have unforeseen impacts, including differing model performance for different user groups, as well as privacy implications. In this paper, we propose an approach to explicitly obscure important author characteristics at training time, such that representations learned are invariant to these attributes. Evaluating on two tasks, we show that this leads to increased privacy in the learned representations, as well as more robust models to varying evaluation conditions, including out-of-domain corpora.<br/>