Style Transfer as Unsupervised Machine Translation

By Zhirui Zhang, Shuo Ren, Shujie Liu, Jianyong Wang, Peng‐Jen Chen, Mu Li, Ming Zhou, Enhong Chen. 2018

74 citations recorded by the source corpus.

Language style transferring rephrases text with specific stylistic attributes while preserving the original attribute-independent content. One main challenge in learning a style transfer system is a lack of parallel data where the source sentence is in one style and the target sentence in another style. With this constraint, in this paper, we adapt unsupervised machine translation methods for the task of automatic style transfer. We first take advantage of style-preference information and word embedding similarity to produce pseudo-parallel data with a statistical machine translation (SMT) framework. Then the iterative back-translation approach is employed to jointly train two neural machine translation (NMT) based transfer systems. To control the noise generated during joint training, a style classifier is introduced to guarantee the accuracy of style transfer and penalize bad candidates in the generated pseudo data. Experiments on benchmark datasets show that our proposed method outperforms previous state-of-the-art models in terms of both accuracy of style transfer and quality of input-output correspondence.

Subfields: Artificial Intelligence, Natural Language Processing

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Artificial Intelligence

In Natural Language Processing

Citations in the corpus

Break-It-Fix-It: Unsupervised Learning for Program Repair (2021, background): “…approach that uses the target-to-source model to generate noisy sources and then trains the source-to-target model to reconstruct the targets (also related to cycle-consistency (Zhu et al., 2017; Hoffman et al., 2018) and style transfer (Shen et al., 2017; Yang et al., 2018; Zhang et al., 2019)).”
Reformulating Unsupervised Style Transfer as Paraphrase Generation (2020, unknown): “We also note that crowdworkers had higher agreement for sentences which were clearly not paraphrases (like the UNMT / DLSM generations on the Formality dataset).”
Multiple-Attribute Text Rewriting (2018, methodology): “The resulting model is similar to recently proposed methods for unsupervised machine translation (Lample et al., 2017a; 2018; Artetxe et al., 2018; Zhang et al., 2018b), but with two major differences: (a) we use a pooling operator which is used to control the trade-off between style transfer and…”
“Transforming” Delete, Retrieve, Generate Approach for Controlled Text Style Transfer (2019, methodology): “This approach has been later encapsulated in encoder-decoder frameworks (Fu et al., 2018; John et al., 2018; Zhang et al., 2018a,b).”
Text Style Transfer: A Review and Experiment Evaluation (2020, methodology): “Zhang et al. [89] proposed and experimented with a few pseudo-parallel dataset generation methods.”
Civil Rephrases Of Toxic Texts With Self-Supervised Transformers (2021, background): “Then, a decoder, aware of the destination attribute, generated a transferred sentence (Shen et al., 2017; Hu et al., 2017; Fu et al., 2018; Zhang et al., 2018c; Xu et al., 2018; John et al., 2019).”
IMaT: Unsupervised Text Attribute Transfer via Iterative Matching and Translation (2019, background): “In the past few years, attribute-controlled NLG has witnessed renewed interest by researchers working on neural approaches to generation (Hu et al., 2017; Jhamtani et al., 2017; Melnyk et al., 2017; Mueller et al., 2017; Zhang et al., 2018; Prabhumoye et al., 2018; Niu and Bansal, 2018).”
Zero-Shot Fine-Grained Style Transfer: Leveraging Distributed Continuous Style Representations to Transfer To Unseen Styles (2019, background): “Recent strides in unsupervised translation have led to a body of work adapting machine translation techniques to style transfer (Prabhumoye et al., 2018; Lample et al., 2019; Zhang et al., 2018).”
Style Transformer: Unpaired Text Style Transfer without Disentangled Latent Representation (2019, methodology): “Following their work, many methods (Fu et al., 2018; John et al., 2018; Zhang et al., 2018a,b) has been proposed based on standard encoder-decoder architecture.”