Style Obfuscation by Invariance
arXiv:1805.07143
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. 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.
arXiv commentAccepted for presentation at COLING18
References in corpus (12)
- Adam: A Method for Stochastic Optimization
- Sequence to Sequence Learning with Neural Networks
- Google's Neural Machine Translation System: Bridging the Gap between Human and Machine Translation
- Enriching Word Vectors with Subword Information
- A Hierarchical Neural Autoencoder for Paragraphs and Documents
- When Coding Style Survives Compilation: De-anonymizing Programmers from Executable Binaries
- Google's Multilingual Neural Machine Translation System: Enabling Zero-Shot Translation
- Adversarial Multi-task Learning for Text Classification
- Controllable Invariance through Adversarial Feature Learning
- Show, Adapt and Tell: Adversarial Training of Cross-domain Image Captioner
- Cross-lingual Distillation for Text Classification
- : Author Attribute Anonymity by Adversarial Training of Neural Machine Translation