CLMay 18, 2018

Style Obfuscation by Invariance

arXiv:1805.07143v11099 citations
Originality Incremental advance
AI Analysis

This addresses privacy and anonymity in text generation for users needing to hide their writing style, but it is incremental as it builds on prior style-transfer frameworks.

The paper tackled the problem of obfuscating writing style without altering semantic content by proposing obfuscation-by-invariance, showing that style classifier performance can be reduced to chance level while maintaining output quality comparable to style-transfer models in automatic evaluations.

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.

Code Implementations1 repo
Foundations

The foundational work for this paper's niche, ranked by how specifically the neighbourhood builds on it — not by global fame.

Your Notes