【NEWS】Our paper was accepted to ACL-IJCNLP 2021 (Findings)
【Title】LEWIS: Levenshtein Editing for Unsupervised Text Style Transfer
【Authors】Machel Reid and Victor Zhong (University of Washington)
【Overview】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.
Our paper was accepted for ACL-IJCNLP 2021 (Findings).
