Abstract
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.- Anthology ID:
- P19-1553
- Volume:
- Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics
- Month:
- July
- Year:
- 2019
- Address:
- Florence, Italy
- Editors:
- Anna Korhonen, David Traum, Lluís Màrquez
- Venue:
- ACL
- SIG:
- Publisher:
- Association for Computational Linguistics
- Note:
- Pages:
- 5527–5532
- Language:
- URL:
- https://aclanthology.org/P19-1553
- DOI:
- 10.18653/v1/P19-1553
- Cite (ACL):
- Canasai Kruengkrai. 2019. Better Exploiting Latent Variables in Text Modeling. In Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics, pages 5527–5532, Florence, Italy. Association for Computational Linguistics.
- Cite (Informal):
- Better Exploiting Latent Variables in Text Modeling (Kruengkrai, ACL 2019)
- PDF:
- https://preview.aclanthology.org/nschneid-patch-1/P19-1553.pdf
- Data
- Penn Treebank