Style Obfuscation by Invariance

Chris Emmery, Enrique Manjavacas Arevalo, Grzegorz Chrupała


Abstract
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. A side effect of this framework are the frequent 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 in parallel and non-parallel settings, and compare automatic and human evaluations on the obfuscated sentences. Our experiments show that the performance of a style classifier can be reduced to chance level, while the output is evaluated to be of equal quality to models applying style-transfer. Additionally, human evaluation indicates a trade-off between the level of obfuscation and the observed quality of the output in terms of meaning preservation and grammaticality.
Anthology ID:
C18-1084
Volume:
Proceedings of the 27th International Conference on Computational Linguistics
Month:
August
Year:
2018
Address:
Santa Fe, New Mexico, USA
Editors:
Emily M. Bender, Leon Derczynski, Pierre Isabelle
Venue:
COLING
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
984–996
Language:
URL:
https://aclanthology.org/C18-1084
DOI:
Bibkey:
Cite (ACL):
Chris Emmery, Enrique Manjavacas Arevalo, and Grzegorz Chrupała. 2018. Style Obfuscation by Invariance. In Proceedings of the 27th International Conference on Computational Linguistics, pages 984–996, Santa Fe, New Mexico, USA. Association for Computational Linguistics.
Cite (Informal):
Style Obfuscation by Invariance (Emmery et al., COLING 2018)
Copy Citation:
PDF:
https://aclanthology.org/C18-1084.pdf
Code
 cmry/style-obfuscation