Paper Review - Disentanglement in NLP
Published:
Mutual Information used in NLP Disentanglement
Introduction
This paper reduces the mutual information in different features in a sentence(like style and content), to disentangle the feature in embedding space.
[Cite]
Cheng, Pengyu, et al. “Improving disentangled text representation learning with information-theoretic guidance.” arXiv preprint arXiv:2006.00693 (2020).
Contact
The above is the a paper review video. If you encounter unclear or controversial issues, feel free to contact Leslie Wong.
