Prompt-Based Editing for Text Style Transfer

01/27/2023
by   Guoqing Luo, et al.
0

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.

READ FULL TEXT

page 1

page 2

page 3

page 4

research
11/14/2022

Replacing Language Model for Style Transfer

We introduce replacing language model (RLM), a sequence-to-sequence lang...
research
04/28/2022

Russian Texts Detoxification with Levenshtein Editing

Text detoxification is a style transfer task of creating neutral version...
research
10/25/2021

Actions Speak Louder than Listening: Evaluating Music Style Transfer based on Editing Experience

The subjective evaluation of music generation techniques has been mostly...
research
06/13/2023

ChatGPT vs Human-authored Text: Insights into Controllable Text Summarization and Sentence Style Transfer

Large-scale language models, like ChatGPT, have garnered significant med...
research
10/19/2019

XL-Editor: Post-editing Sentences with XLNet

While neural sequence generation models achieve initial success for many...
research
06/14/2022

Text Generation with Text-Editing Models

Text-editing models have recently become a prominent alternative to seq2...
research
01/24/2023

Audience-Centric Natural Language Generation via Style Infusion

Adopting contextually appropriate, audience-tailored linguistic styles i...

Please sign up or login with your details

Forgot password? Click here to reset