Text attribute transfer using non-parallel data requires methods that can perform disentanglement of content and linguistic attributes. In this work, we propose multiple improvements over the existing approaches that enable the encoder-decoder framework to cope with the text attribute transfer from non-parallel data. We perform experiments on the sentiment transfer task using two datasets. For both datasets, our proposed method outperforms a strong baseline in two of the three employed evaluation metrics.
@article{arxiv.1711.09395,
title = {Improved Neural Text Attribute Transfer with Non-parallel Data},
author = {Igor Melnyk and Cicero Nogueira dos Santos and Kahini Wadhawan and Inkit Padhi and Abhishek Kumar},
journal= {arXiv preprint arXiv:1711.09395},
year = {2017}
}
Comments
NIPS 2017 Workshop on Learning Disentangled Representations: from Perception to Control