Variational Attention for Sequence-to-Sequence Models

Method and contribution

Treats attention context vectors as Gaussian latent variables in a variational encoder-decoder.

Clarifies that the term variational attention also names a different random object: the context vector.

Read in context

Attention as a Latent Variable: Modeling a Distribution over Attention →

Citation

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}
}