XFORMAL: A Benchmark for Multilingual Formality Style Transfer
arXiv:2104.04108
Abstract
We take the first step towards multilingual style transfer by creating and releasing XFORMAL, a benchmark of multiple formal reformulations of informal text in Brazilian Portuguese, French, and Italian. Results on XFORMAL suggest that state-of-the-art style transfer approaches perform close to simple baselines, indicating that style transfer is even more challenging when moving multilingual.
arXiv commentNAACL 2021
References in corpus (5)
- The Sockeye 2 Neural Machine Translation Toolkit at AMTA 2020
- Unpaired Sentiment-to-Sentiment Translation: A Cycled Reinforcement Learning Approach
- A Dual Reinforcement Learning Framework for Unsupervised Text Style Transfer
- Style Transfer for Texts: Retrain, Report Errors, Compare with Rewrites
- Grammatical Error Correction and Style Transfer via Zero-shot Monolingual Translation