Two types of knowledge, triples from knowledge graphs and texts from unstructured documents, have been studied for knowledge aware open-domain conversation generation, in which triple attributes or graph paths can narrow down vertex candidates for knowledge selection decision, and texts can provide rich information for response generation. Fusion of a knowledge graph and texts might yield mutually reinforcing advantages for conversation generation, but there is less study on that. To address this challenge, we propose a knowledge aware chatting machine with three components, an augmented knowledge graph containing both triples and texts, knowledge selector, and response generator. For knowledge selection on the graph, we formulate it as a problem of multi-hop graph reasoning that is more explainable and flexible in comparison with previous works. To fully leverage long text information that differentiates our graph from others, we improve a state of the art reasoning algorithm with machine reading comprehension technology. We demonstrate that supported by such unified knowledge and explainable knowledge selection method, our system can generate more appropriate and informative responses than baselines.
翻译:两种类型的知识,即知识图和来自非结构化文件的文本的三重知识,已经为知识意识的开放域对话生成进行了研究,其中三重属性或图形路径可以缩小用于知识选择决定的顶点候选人,而文本可以提供丰富的信息进行响应生成。知识图和文本的融合可以为对话生成产生相辅相成的优势,但这方面的研究较少。为了应对这一挑战,我们提议了一种知识意识聊天机,其中有三个组成部分,一个强化知识图,其中包含三重文本、知识选择器和反应生成器。关于在图形上选择知识,我们把它设计成一个多点图推理的问题,与以往的工程相比,它更能解释,更灵活。要充分利用长文本信息,将我们的图表与其他图表区别开来,我们用机器阅读理解技术来改进艺术推理算法的状况。我们证明,这种统一知识和解释性知识选择方法的支持,我们的系统能够产生比基线更合适和更加丰富的信息反应。