Open zhou1xiang2 opened 5 years ago
For privacy reasons, I cannot publish the Beer Advocate dataset here, you can find it in the paper "Zachary C Lipton, Sharad Vikram, and Julian McAuley. Generative concatenative nets jointly learn to write and classify reviews. CoRR, abs/1511.03683, 2015".
As for the code, I have provided it. You only need to modify the model parameter "label_size" ( https://github.com/Nrgeup/controllable-text-attribute-transfer/blob/master/method/mymodel-yelp/main.py#L54 ).
As for outputs, I have shown examples in the supplementary material (“0.3 Multi-aspect Attribute Transfer Cases” in https://papers.nips.cc/paper/2019/file/8804f94e16ba5b680e239a554a08f7d2-Supplemental.zip)
Thank you!
Could you provide detailed information of for Multi-Aspect Sentiment Transfer experiment ? (model code, input data and output data)