Learning to Generate Multiple Style Transfer Outputs for an Input Sentence

Kevin Lin, Ming-Yu Liu, Ming-Ting Sun, Jan Kautz


Abstract
Text style transfer refers to the task of rephrasing a given text in a different style. While various methods have been proposed to advance the state of the art, they often assume the transfer output follows a delta distribution, and thus their models cannot generate different style transfer results for a given input text. To address the limitation, we propose a one-to-many text style transfer framework. In contrast to prior works that learn a one-to-one mapping that converts an input sentence to one output sentence, our approach learns a one-to-many mapping that can convert an input sentence to multiple different output sentences, while preserving the input content. This is achieved by applying adversarial training with a latent decomposition scheme. Specifically, we decompose the latent representation of the input sentence to a style code that captures the language style variation and a content code that encodes the language style-independent content. We then combine the content code with the style code for generating a style transfer output. By combining the same content code with a different style code, we generate a different style transfer output. Extensive experimental results with comparisons to several text style transfer approaches on multiple public datasets using a diverse set of performance metrics validate effectiveness of the proposed approach.
Anthology ID:
2020.ngt-1.2
Volume:
Proceedings of the Fourth Workshop on Neural Generation and Translation
Month:
July
Year:
2020
Address:
Online
Venues:
ACL | NGT | WS
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
10–23
Language:
URL:
https://aclanthology.org/2020.ngt-1.2
DOI:
10.18653/v1/2020.ngt-1.2
Bibkey:
Cite (ACL):
Kevin Lin, Ming-Yu Liu, Ming-Ting Sun, and Jan Kautz. 2020. Learning to Generate Multiple Style Transfer Outputs for an Input Sentence. In Proceedings of the Fourth Workshop on Neural Generation and Translation, pages 10–23, Online. Association for Computational Linguistics.
Cite (Informal):
Learning to Generate Multiple Style Transfer Outputs for an Input Sentence (Lin et al., NGT 2020)
Copy Citation:
PDF:
https://aclanthology.org/2020.ngt-1.2.pdf
Video:
 http://slideslive.com/38929815