Towards Universality in Multilingual Text Rewriting
This addresses the challenge of flexible text manipulation across languages for applications like translation and style adaptation, representing a significant advance rather than an incremental improvement.
The paper tackles the problem of building a universal multilingual text rewriter that can modify text attributes like style and language while preserving semantics, achieving state-of-the-art results in unsupervised translation and demonstrating zero-shot capabilities for sentiment transfer and formality-sensitive translation.
In this work, we take the first steps towards building a universal rewriter: a model capable of rewriting text in any language to exhibit a wide variety of attributes, including styles and languages, while preserving as much of the original semantics as possible. In addition to obtaining state-of-the-art results on unsupervised translation, we also demonstrate the ability to do zero-shot sentiment transfer in non-English languages using only English exemplars for sentiment. We then show that our model is able to modify multiple attributes at once, for example adjusting both language and sentiment jointly. Finally, we show that our model is capable of performing zero-shot formality-sensitive translation.