Learning from Bootstrapping and Stepwise Reinforcement Reward: A Semi-Supervised Framework for Text Style Transfer. (arXiv:2205.09324v1 [cs.CL])

Text style transfer is an important task in controllable language generation.
Supervised approaches have pushed performance improvement on style-oriented
rewriting such as formality conversion. However, challenges remain due to the
scarcity of large-scale parallel data in many domains. While unsupervised
approaches do not rely on annotated sentence pairs for each style, they are
often plagued with instability issues such as mode collapse or quality
degradation. To take advantage of both supervised and unsupervised paradigms
and tackle the challenges, in this …

arxiv bootstrapping framework learning reinforcement semi-supervised style transfer text text style transfer transfer