Privacy-aware text rewriting

Qiongkai Xu, Lizhen Qu, Chenchen Xu, Ran Cui

Research output: Chapter in Book/Report/Conference proceedingConference PaperResearch

16 Citations (Scopus)


Biased decisions made by automatic systems have led to growing concerns in research communities. Recent work from the NLP community focuses on building systems that make fair decisions based on text. Instead of relying on unknown decision systems or human decision-makers, we argue that a better way to protect data providers is to remove the trails of sensitive information before publishing the data. In light of this, we propose a new privacy-aware text rewriting task and explore two privacy-aware back-translation methods for the task, based on adversarial training and approximate fairness risk. Our extensive experiments on three real-world datasets with varying demo-graphical attributes show that our methods are effective in obfuscating sensitive attributes. We have also observed that the fairness risk method retains better semantics and fluency, while the adversarial training method tends to leak less sensitive information.

Original languageEnglish
Title of host publicationINLG 2019 - The 12th International Conference on Natural Language Generation - Proceedings of the Conference
EditorsKees Deemter, Chenhgua Lin, Hiroya Takamura
Place of PublicationStroudsburg PA USA
PublisherAssociation for Computational Linguistics (ACL)
Number of pages11
ISBN (Electronic)9781950737949
Publication statusPublished - 2019
EventInternational Conference on Natural Language Generation 2019 - Tokyo, Japan
Duration: 29 Oct 20191 Nov 2019
Conference number: 12th (Proceedings) (Website)


ConferenceInternational Conference on Natural Language Generation 2019
Abbreviated titleINLG 2019
Internet address

Cite this