Variational Attention for Sequence-to-Sequence Models

方法与贡献

在变分编码器—解码器中，把注意力上下文向量视为高斯隐变量。

说明“变分注意力”这一名称也用于另一个随机对象：上下文向量。

结合主题阅读

把注意力建模为隐变量：学习注意力的概率分布 →

引用

Hareesh Bahuleyan, Lili Mou, Olga Vechtomova, Pascal Poupart. Variational Attention for Sequence-to-Sequence Models. COLING 2018.

@inproceedings{bahuleyan2018variational,
  title = {{Variational Attention for Sequence-to-Sequence Models}},
  author = {Bahuleyan, Hareesh and Mou, Lili and Vechtomova, Olga and Poupart, Pascal},
  year = {2018},
  booktitle = {COLING 2018},
  url = {https://aclanthology.org/C18-1142/},
  eprint = {1712.08207},
  archivePrefix = {arXiv}
}