CLAILGJan 27, 2023

Prompt-Based Editing for Text Style Transfer

arXiv:2301.11997v2140 citationsh-index: 35
AI Analysis

This addresses the controllability issue in text style transfer for natural language processing applications, representing a novel method rather than an incremental improvement.

The paper tackles the problem of text style transfer by proposing a prompt-based editing approach that transforms generation into classification, achieving state-of-the-art performance on three benchmark datasets while using 20 times fewer parameters than existing systems.

Prompting approaches have been recently explored in text style transfer, where a textual prompt is used to query a pretrained language model to generate style-transferred texts word by word in an autoregressive manner. However, such a generation process is less controllable and early prediction errors may affect future word predictions. In this paper, we present a prompt-based editing approach for text style transfer. Specifically, we prompt a pretrained language model for style classification and use the classification probability to compute a style score. Then, we perform discrete search with word-level editing to maximize a comprehensive scoring function for the style-transfer task. In this way, we transform a prompt-based generation problem into a classification one, which is a training-free process and more controllable than the autoregressive generation of sentences. In our experiments, we performed both automatic and human evaluation on three style-transfer benchmark datasets, and show that our approach largely outperforms the state-of-the-art systems that have 20 times more parameters. Additional empirical analyses further demonstrate the effectiveness of our approach.

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