Multilingual Pre-training with Language and Task Adaptation for Multilingual Text Style Transfer
This addresses the problem of limited parallel data for multilingual style transfer, offering a modular approach that is applicable to other tasks and languages.
The paper tackled multilingual text style transfer by adapting the pre-trained mBART model with machine-translated and gold-aligned English data, achieving state-of-the-art results in three target languages.
We exploit the pre-trained seq2seq model mBART for multilingual text style transfer. Using machine translated data as well as gold aligned English sentences yields state-of-the-art results in the three target languages we consider. Besides, in view of the general scarcity of parallel data, we propose a modular approach for multilingual formality transfer, which consists of two training strategies that target adaptation to both language and task. Our approach achieves competitive performance without monolingual task-specific parallel data and can be applied to other style transfer tasks as well as to other languages.