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.
翻译:目前,端到端深的基于深层学习的开放域对话系统仍然是黑盒模型,因此很容易生成与数据驱动模型无关的内容。具体地说,潜伏变量与潜在空间的不同语义高度纠缠在一起,因为缺乏指导培训的先验知识。为解决这一问题,本文件提议通过涉及中观尺度特征分解的认知方法,利用先验知识来利用先验知识来利用基因模型。特别是,该模型将宏观级指导类知识和微观级开放域对话数据结合到培训中,利用先验知识进入潜藏空间,使模型能够分解中观空间范围内的潜在变量。此外,我们提出了新的开放域对话指标,可以客观地评估潜在空间分布的可解释性。最后,我们验证了我们关于不同数据集的模型,并实验性地证明我们的模型能够产生比其他模型更高质量和更多可解释的对话。