Style Obfuscation by Invariance

Chris Emmery*, Enrique Manjavacas, Grzegorz Chrupala

*Corresponding author for this work

Research output: Chapter in Book/Report/Conference proceedingConference contributionScientificpeer-review


The task of obfuscating writing style using sequence models has previously been investigated under the framework of obfuscation-by-transfer, where the input text is explicitly rewritten in another style. These approaches also often lead to major alterations to the semantic content of the input. In this work, we propose obfuscation-by-invariance, and investigate to what extent models trained to be explicitly style-invariant preserve semantics. We evaluate our architectures on parallel and non-parallel corpora, and compare automatic and human evaluations on the obfuscated sentences. Our experiments show that style classifier performance can be reduced to chance level, whilst the automatic evaluation of the output is seemingly equal to models applying style-transfer. However, based on human evaluation we demonstrate a trade-off between the level of obfuscation and the observed quality of the output in terms of meaning preservation and grammaticality.
Original languageEnglish
Title of host publicationCOLING 2018
PublisherAssociation for Computational Linguistics
Number of pages12
Publication statusPublished - Aug 2018
EventInternational Conference on Computational Linguistics 2018 - Santa Fe Community Convention Center, Santa Fe, United States
Duration: 20 Aug 201826 Aug 2018
Conference number: 27


ConferenceInternational Conference on Computational Linguistics 2018
Abbreviated titleCOLING 2018
Country/TerritoryUnited States
CitySanta Fe
Internet address


Dive into the research topics of 'Style Obfuscation by Invariance'. Together they form a unique fingerprint.

Cite this