Interpreting open-domain dialogue generation by disentangling latent feature representations

Currently end-to-end deep learning based open-domain dialogue systems remain black box models, making it easy to generate irrelevant contents with data-driven models. Specifically, latent variables are highly entangled with different semantics in the latent space due to the lack of priori knowledge to guide the training. To address this problem, this paper proposes to harness the generative model with a priori knowledge through a cognitive approach involving feature disentanglement. Particularly, the model integrates the guided-category knowledge and open-domain dialogue data for the training, leveraging the priori knowledge into the latent space, which enables the model to disentangle the latent variables. Besides, this paper proposes a new metric for open-domain dialogues, which can objectively evaluate the interpretability of the latent space distribution. Finally, this paper validates our model on different datasets and experimentally demonstrate that our model is able to generate higher quality and more interpretable dialogues than other models.