LEWIS: Levenshtein Editing for Unsupervised Text Style Transfer
By Machel Reid, Victor Zhong. 2021
75 citations recorded by the source corpus.
Many types of text style transfer can be achieved with only small, precise edits (e.g. sentiment transfer from I had a terrible time... to I had a great time...). We propose a coarse-to-fine editor for style transfer that transforms text using Levenshtein edit operations (e.g. insert, replace, delete). Unlike prior single-span edit methods, our method concurrently edits multiple spans in the source text. To train without parallel style text pairs (e.g. pairs of +/- sentiment statements), we propose an unsupervised data synthesis procedure. We first convert text to style-agnostic templates using style classifier attention (e.g. I had a SLOT time...), then fill in slots in these templates using fine-tuned pretrained language models. Our method outperforms existing generation and editing style transfer methods on sentiment (Yelp, Amazon) and politeness (Polite) transfer. In particular, multi-span editing achieves higher performance and more diverse output than single-span editing. Moreover, compared to previous methods on unsupervised data synthesis, our method results in higher quality parallel style pairs and improves model performance.
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
- Graham Neubig
- Matt Gardner
- Matthew E. Peters
- Mohit Bansal
- Hao Peng
- Noah A. Smith
- Luke S. Zettlemoyer
- Tongshuang Sherry Wu
In Natural Language Processing
- Graham Neubig
- Matt Gardner
- Matthew E. Peters
- Hao Peng
- Tongshuang Sherry Wu
- Mohit Bansal
- Alexis Ross
- Luke S. Zettlemoyer
Citations in the corpus
- Tailor: Generating and Perturbing Text with Semantic Controls (2021, methodology): “Controllable text generation has been widely used to influence various properties of generated text for text summarization (Peng et al., 2019), data augmentation (Lee et al., 2021), style transfer (Reid and Zhong, 2021; Madaan et al., 2020a), adversarial example generation (Iyyer et al., 2018), etc.”
- Learning to Model Editing Processes (2022, methodology): “We first note that our model significantly outperforms LEWIS (Reid and Zhong, 2021) on WIKIREVISIONS, by 8.”