陈俊帆
点赞：
陈俊帆
点赞：
论文
Text Style Transferring via Adversarial Masking and Styled Filling
发布时间：2025-10-22点击次数：
发表刊物：
Proceedings of the 2022 Conference on Empirical Methods in Natural Language Processing (EMNLP), CCF-B
摘要：
Text style transfer is an important task in natural language processing with broad applications. Existing models following the masking and filling scheme suffer two challenges: the word masking procedure may mistakenly remove unexpected words and the selected words in the word filling procedure may lack diversity and semantic consistency. To tackle both challenges, in this study, we propose a style transfer model, with an adversarial masking approach and a styled filling technique (AMSF). Specifically, AMSF first trains a mask predictor by adversarial training without manual configuration. Then two additional losses, i.e. an entropy maximization loss and a consistency regularization loss, are introduced in training the word filling module to guarantee the diversity and semantic consistency of the transferred texts. Experimental results and analysis on two benchmark text style transfer data sets demonstrate the effectiveness of the proposed approaches.
合写作者：
Jiarui Wang,张日崇,陈俊帆, Jaein Kim, Yongyi Mao
论文类型：
国际学术会议
页面范围：
7654-7663
是否译文：
否
发表时间：
2022-01-01