论文标题
动态知识基于图形的对话生成，并改进了对抗性元学习
Dynamic Knowledge Graph-based Dialogue Generation with Improved Adversarial Meta-Learning
论文作者
论文摘要
基于知识图的对话系统能够产生更多信息响应，并可以实施复杂的推理机制。但是，这些模型没有考虑到知识图（kg）的稀疏性和不完整性，并且当前的对话模型不能应用于动态kg。本文提出了一种基于动态知识图的对话生成方法，并通过改进的对抗元学习（KDAD）提出。 KDAD将动态知识三元化为对抗性攻击问题，并结合了快速适应动态知识意识的对话生成的目标。我们使用最小的培训样本训练基于知识图的对话模型，并改进了ADML。该模型可以初始化参数并适应以前的看不见的知识，以便仅基于几个知识三元组就可以快速完成培训。我们表明，我们的模型大大优于其他基线。我们评估并证明我们的方法非常快速地适应基于图形的动态知识对话的产生。
Knowledge graph-based dialogue systems are capable of generating more informative responses and can implement sophisticated reasoning mechanisms. However, these models do not take into account the sparseness and incompleteness of knowledge graph (KG)and current dialogue models cannot be applied to dynamic KG. This paper proposes a dynamic Knowledge graph-based dialogue generation method with improved adversarial Meta-Learning (KDAD). KDAD formulates dynamic knowledge triples as a problem of adversarial attack and incorporates the objective of quickly adapting to dynamic knowledge-aware dialogue generation. We train a knowledge graph-based dialog model with improved ADML using minimal training samples. The model can initialize the parameters and adapt to previous unseen knowledge so that training can be quickly completed based on only a few knowledge triples. We show that our model significantly outperforms other baselines. We evaluate and demonstrate that our method adapts extremely fast and well to dynamic knowledge graph-based dialogue generation.
