论文标题
辩护：知识结构意识到以任务为导向的对话生成
DialoKG: Knowledge-Structure Aware Task-Oriented Dialogue Generation
论文作者
论文摘要
以任务为导向的对话生成具有挑战性，因为基本知识通常是动态的，并且有效地将知识纳入学习过程很难。在这种情况下，同时产生类似人类和信息的反应是尤其具有挑战性的。最近的研究主要集中在各种知识蒸馏方法上，在这些方法中，知识库中事实之间的基本关系没有被有效地捕获。在本文中，我们迈进了一步，并演示知识图的结构信息如何改善系统的推理功能。具体来说，我们提出了一种新颖的面向任务的对话系统Dialokg，可有效地将知识纳入语言模型。我们提出的系统将关系知识视为知识图，并介绍了（1）结构感知的知识嵌入技术，以及（2）知识的图形加权掩盖屏蔽策略，以促进系统在对话生成期间选择相关信息的系统。经验评估表明，对辩证的有效性比几个标准基准数据集对最先进的方法的有效性。
Task-oriented dialogue generation is challenging since the underlying knowledge is often dynamic and effectively incorporating knowledge into the learning process is hard. It is particularly challenging to generate both human-like and informative responses in this setting. Recent research primarily focused on various knowledge distillation methods where the underlying relationship between the facts in a knowledge base is not effectively captured. In this paper, we go one step further and demonstrate how the structural information of a knowledge graph can improve the system's inference capabilities. Specifically, we propose DialoKG, a novel task-oriented dialogue system that effectively incorporates knowledge into a language model. Our proposed system views relational knowledge as a knowledge graph and introduces (1) a structure-aware knowledge embedding technique, and (2) a knowledge graph-weighted attention masking strategy to facilitate the system selecting relevant information during the dialogue generation. An empirical evaluation demonstrates the effectiveness of DialoKG over state-of-the-art methods on several standard benchmark datasets.
