Formality Style Transfer with Hybrid Textual Annotations
This work addresses the problem of data scarcity in formality style transfer for natural language processing applications, with incremental improvements in performance.
The paper tackles the challenge of formality style transfer by proposing an omnivorous model that uses both parallel and formality-classified data to address data sparsity, achieving state-of-the-art performance on a benchmark dataset and competitive results on other unsupervised text style transfer tasks.
Formality style transformation is the task of modifying the formality of a given sentence without changing its content. Its challenge is the lack of large-scale sentence-aligned parallel data. In this paper, we propose an omnivorous model that takes parallel data and formality-classified data jointly to alleviate the data sparsity issue. We empirically demonstrate the effectiveness of our approach by achieving the state-of-art performance on a recently proposed benchmark dataset of formality transfer. Furthermore, our model can be readily adapted to other unsupervised text style transfer tasks like unsupervised sentiment transfer and achieve competitive results on three widely recognized benchmarks.