Monolingual and Cross-lingual Zero-shot Style Transfer
This addresses style adaptation in multilingual NLP, but is incremental as it builds on prior zero-shot work.
The paper tackles zero-shot style transfer between languages without parallel style data, proposing a multilingual multi-style machine translation system that achieves up to 3x increase in dissimilar style presence and handles contractions and lexicon swaps effectively.
We introduce the task of zero-shot style transfer between different languages. Our training data includes multilingual parallel corpora, but does not contain any parallel sentences between styles, similarly to the recent previous work. We propose a unified multilingual multi-style machine translation system design, that allows to perform zero-shot style conversions during inference; moreover, it does so both monolingually and cross-lingually. Our model allows to increase the presence of dissimilar styles in corpus by up to 3 times, easily learns to operate with various contractions, and provides reasonable lexicon swaps as we see from manual evaluation.