DGST: a Dual-Generator Network for Text Style Transfer

Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing, pages 7131–7136, November 16–20, 2020. c⃝2020 Association for Computational Linguistics 7131 DGST: a Dual-Generator Network for Text Style Transfer Xiao Li♠, Guanyi Chen♥, Chenghua Lin♠∗, Ruizhe Li♠ ♠Department of Computer Science, University of Sheffield ♥Department of Information and Computing Sciences, Utrecht University {xiao.li, c.lin, r.li}@sheffield.ac.uk, g.chen@uu.nl Abstract We propose DGST, a novel and simple Dual- Generator network architecture for text Style Transfer. Our model employs two generators only, and does not rely on any discriminators or parallel corpus for training. Both quantita- tive and qualitative experiments on the Yelp and IMDb datasets show that our model gives competitive performance compared to several strong baselines with more complicated archi- tecture designs. 1 Introduction Attribute style transfer is a task which seeks to change a stylistic attribute of text, while preserving its attribute-independent information. Sentiment transfer is a typical example of such kind, which focuses on controlling the sentiment polarity of the input text (Shen et al., 2017). Given a review “the service was very poor”, a successful sentiment transferrer should covert the negative sentiment of the input to positive (e.g., replacing the phrase “very poor” with “pretty good”), while keeping all other information unchanged (e.g., the aspect “ser- vice” should not being changed to “food”). Without supervised signals from parallel data, a transferrer must be supervised in a way to en- sure that the generated texts belongs to a certain style category (i.e., transfer intensity). There is a growing body of studies to intensify the target style by means of adversarial training (Fu et al., 2018), variational autoencoder (John et al., 2019; Li et al., 2019; Fang et al., 2019), generative adversarial nets (Shen et al., 2017; Zhao et al., 2018; Yang et al., 2018), or subspace matrix projection (Li et al., 2020) Furthermore, in order to boost the preservation of non-attribute information during style transfor- mation, some works explicitly focus on modify- ∗Corresponding author ing sentiment words, which is so-called the “pivot word” (Li et al., 2018; Wu et al., 2019). There are also works which add extra components for con- straining the content from being changed too much. These include models like autoencoder (Lample et al., 2019; Dai et al., 2019), part-of-speech preservation, and the content conditional language model (Tian et al., 2018). In order to achieve high- quality style transfer, existing works normally re- sort to adding additional inner or outer structures such as additional adversarial networks or data pre- processing steps (e.g. generating pseudo-parallel corpora). This inevitably increases the complex- ity of the model and raises the bar of training data requirement. In this paper, we propose a novel and simple model architecture for text style transfer, which employs two generators only. In contrast to some of the dominant approaches to style transfer such as CycleGAN (Zhu et al., 2017), our model does not employ any discriminators and yet can be trained without requiring any parallel corpus. We achieve this by developing a novel sentence …

Content truncated to 500 words