Abstract
Unsupervised text style transfer aims to alter text styles while preserving the content, without aligned data for supervision. Existing seq2seq methods face three challenges: 1) the transfer is weakly interpretable, 2) generated outputs struggle in content preservation, and 3) the trade-off between content and style is intractable. To address these challenges, we propose a hierarchical reinforced sequence operation method, named Point-Then-Operate (PTO), which consists of a high-level agent that proposes operation positions and a low-level agent that alters the sentence. We provide comprehensive training objectives to control the fluency, style, and content of the outputs and a mask-based inference algorithm that allows for multi-step revision based on the single-step trained agents. Experimental results on two text style transfer datasets show that our method significantly outperforms recent methods and effectively addresses the aforementioned challenges.
Abstract (translated)
无监督的文本样式转换旨在在保留内容的同时更改文本样式，而无需对数据进行监督。现有的seq2seq方法面临三个挑战：1）传递的解释能力较弱；2）生成的输出在内容保存方面存在困难；3）内容和风格之间的权衡难以解决。为了解决这些挑战，我们提出了一种分层增强的序列操作方法，即点然后操作（PTO），它由一个提出操作位置的高级代理和一个改变句子的低级代理组成。我们提供了全面的培训目标，以控制输出的流畅性、风格和内容，以及一个基于掩码的推理算法，允许基于单步训练的代理进行多步修订。对两个文本式传输数据集的实验结果表明，我们的方法明显优于最近的方法，并有效地解决了上述挑战。
URL
https://arxiv.org/abs/1906.01833
