Variational Self-attention Model for Sentence Representation

원문 초록

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.