A Hierarchical Reinforced Sequence Operation Method for Unsupervised Text Style Transfer
This work addresses challenges in text style transfer for natural language processing applications, representing an incremental improvement with a novel method for known bottlenecks.
The paper tackled the problem of unsupervised text style transfer by proposing a hierarchical reinforced sequence operation method to improve interpretability, content preservation, and the trade-off between content and style, achieving significant performance gains over recent methods on two datasets.
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.