English

Variational Self-attention Model for Sentence Representation

Computation and Language 2020-03-11 v4

Abstract

This paper proposes a variational self-attention model (VSAM) that employs variational inference to derive self-attention. We model the self-attention vector as random variables by imposing a probabilistic distribution. The self-attention mechanism summarizes source information as an attention vector by weighted sum, where the weights are a learned probabilistic distribution. Compared with conventional deterministic counterpart, the stochastic units incorporated by VSAM allow multi-modal attention distributions. Furthermore, by marginalizing over the latent variables, VSAM is more robust against overfitting. Experiments on the stance detection task demonstrate the superiority of our method.

Keywords

Cite

@article{arxiv.1812.11559,
  title  = {Variational Self-attention Model for Sentence Representation},
  author = {Qiang Zhang and Shangsong Liang and Emine Yilmaz},
  journal= {arXiv preprint arXiv:1812.11559},
  year   = {2020}
}

Comments

arXiv admin note: text overlap with arXiv:1511.06038 by other authors

R2 v1 2026-06-23T06:59:12.630Z