ML Anthology

Towards Better Variational Encoder-Decoders in Seq2Seq Tasks

Xiaoyu Shen, Hui Su
AAAI 2018 pp. 8155-8156
doi:10.1609/AAAI.V32I1.12157 /aaai/2018/shen2018aaai-better/

Abstract

Variational encoder-decoders have shown promising results in seq2seq tasks. However, the training process is known difficult to be controlled because latent variables tend to be ignored while decoding. In this paper, we thoroughly analyze the reason behind this training difficulty, compare different ways of alleviating it and propose a new framework that helps significantly improve the overall performance.

PDF AAAI Semantic Scholar

Cite

Text

Shen and Su. "Towards Better Variational Encoder-Decoders in Seq2Seq Tasks." AAAI Conference on Artificial Intelligence, 2018. doi:10.1609/AAAI.V32I1.12157

Markdown

[Shen and Su. "Towards Better Variational Encoder-Decoders in Seq2Seq Tasks." AAAI Conference on Artificial Intelligence, 2018.](https://mlanthology.org/aaai/2018/shen2018aaai-better/) doi:10.1609/AAAI.V32I1.12157

BibTeX

@inproceedings{shen2018aaai-better,
  title     = {{Towards Better Variational Encoder-Decoders in Seq2Seq Tasks}},
  author    = {Shen, Xiaoyu and Su, Hui},
  booktitle = {AAAI Conference on Artificial Intelligence},
  year      = {2018},
  pages     = {8155-8156},
  doi       = {10.1609/AAAI.V32I1.12157},
  url       = {https://mlanthology.org/aaai/2018/shen2018aaai-better/}
}