Official code and data repository for our EMNLP 2020 long paper "Reformulating Unsupervised Style Transfer as Paraphrase Generation" (https://arxiv.org/abs/2010.05700).
Hello,
Thanks for sharing your awesome research and codes. Would you mind sharing some details on how to use the huggingFace models?
I'm using generate API on some examples but the results I'm getting are not very promising. I've also used a two-step pipeline (base paraphrase -> style-specific transfer) but the output of the second step was the exact copy of the base paraphrase model.
Also, any thoughts on fine-tuning this model for another language? I appreciate any feedback.
Hello, Thanks for sharing your awesome research and codes. Would you mind sharing some details on how to use the huggingFace models? I'm using generate API on some examples but the results I'm getting are not very promising. I've also used a two-step pipeline (base paraphrase -> style-specific transfer) but the output of the second step was the exact copy of the base paraphrase model. Also, any thoughts on fine-tuning this model for another language? I appreciate any feedback.