Advanced Conditional Variational Autoencoders (A-CVAE): Towards interpreting open-domain conversation generation via disentangling latent feature representation
This addresses the interpretability issue in open-domain dialogue generation for AI systems, though it appears incremental as it builds on existing CVAE frameworks.
The paper tackles the problem of black-box open-domain dialogue systems generating irrelevant content by proposing Advanced Conditional Variational Autoencoders (A-CVAE) that use macro-level guided-category knowledge and micro-level dialogue data to disentangle latent variables at a mesoscopic scale, resulting in higher quality and more interpretable dialogues than other models.
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 mesoscopic scale feature disentanglement. Particularly, the model integrates the macro-level guided-category knowledge and micro-level open-domain dialogue data for the training, leveraging the priori knowledge into the latent space, which enables the model to disentangle the latent variables within the mesoscopic scale. Besides, we propose a new metric for open-domain dialogues, which can objectively evaluate the interpretability of the latent space distribution. Finally, we validate our model on different datasets and experimentally demonstrate that our model is able to generate higher quality and more interpretable dialogues than other models.