While neural conversation models have shown great potentials towards generating informative and engaging responses via introducing external knowledge, learning such a model often requires knowledge-grounded dialogues that are difficult to obtain. To overcome the data challenge and reduce the cost of building a knowledge-grounded dialogue system, we explore the problem under a zero-resource setting by assuming no context-knowledge-response triples are needed for training. To this end, we propose representing the knowledge that bridges a context and a response and the way that the knowledge is expressed as latent variables, and devise a variational approach that can effectively estimate a generation model from a dialogue corpus and a knowledge corpus that are independent with each other. Evaluation results on three benchmarks of knowledge-grounded dialogue generation indicate that our model can achieve comparable performance with state-of-the-art methods that rely on knowledge-grounded dialogues for training, and exhibits a good generalization ability over different topics and different datasets.
翻译:虽然神经对话模式在通过引进外部知识产生信息化和互动反应方面显示出巨大的潜力,但学习这种模式往往需要难以获得的知识型对话。为了克服数据挑战并降低建立知识型对话系统的成本,我们假设培训不需要环境-知识-应对三重培训,从而在零资源环境下探索问题。为此,我们建议代表一种知识,即将背景和反应联系起来,以及将知识表述为潜在变量的方式,并设计一种可变方法,以有效估计对话体和知识型体的一代模式,而这种知识型体又彼此独立。关于三个知识型对话基准的评价结果表明,我们的模式可以取得可资比较的业绩,采用依靠知识型对话进行培训的先进方法,并展示不同专题和不同数据集的良好概括能力。