Publications
カンファレンス (国際) Better Exploiting Latent Variables in Text Modeling
Canasai Kruengkrai
The 57th Annual Meeting of the Association for Computational Linguistics poster (ACL-2019)
2019.7.31
We show that sampling latent variables multiple
times at a gradient step helps in improving
a variational autoencoder and propose a simple
and effective method to better exploit these latent
variables through hidden state averaging.
Consistent gains in performance on two different
datasets, Penn Treebank and Yahoo, indicate
the generalizability of our method.
Software Download (28KB)
Paper : Better Exploiting Latent Variables in Text Modeling （外部サイト）