Journal:Proceedings of the 2022 Conference on Empirical Methods in Natural Language Processing (EMNLP), CCF-B
Abstract: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.
Co-author:Jiarui Wang,Richong Zhang,Junfan Chen, Jaein Kim, Yongyi Mao
Indexed by:国际学术会议
Page Number:7654-7663
Translation or Not:no
Date of Publication:2022-01-01