IMaT: Unsupervised Text Attribute Transfer via Iterative Matching and Translation
This addresses the challenge of rewriting sentences with specific attributes while preserving content for natural language processing applications, representing a novel method rather than an incremental improvement.
The paper tackles the problem of text attribute transfer without supervised parallel data by proposing IMaT, which constructs a pseudo-parallel corpus and iteratively refines it, achieving large-margin improvements over state-of-the-art systems in sentiment modification and formality transfer tasks.
Text attribute transfer aims to automatically rewrite sentences such that they possess certain linguistic attributes, while simultaneously preserving their semantic content. This task remains challenging due to a lack of supervised parallel data. Existing approaches try to explicitly disentangle content and attribute information, but this is difficult and often results in poor content-preservation and ungrammaticality. In contrast, we propose a simpler approach, Iterative Matching and Translation (IMaT), which: (1) constructs a pseudo-parallel corpus by aligning a subset of semantically similar sentences from the source and the target corpora; (2) applies a standard sequence-to-sequence model to learn the attribute transfer; (3) iteratively improves the learned transfer function by refining imperfections in the alignment. In sentiment modification and formality transfer tasks, our method outperforms complex state-of-the-art systems by a large margin. As an auxiliary contribution, we produce a publicly-available test set with human-generated transfer references.