Dynamic Knowledge Graph-Based Dialogue Generation with Improved Adversarial Meta-Learning

Abstract

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 cannot be applied to dynamic KG. This paper proposes a dynamic Knowledge graph-based dialogue generation method with improved adversarial Meta-Learning (ADML). ADML formulates dynamic knowledge triples as a problem of adversarial attack and incorporates the objective of quickly adapting to dynamic knowledge-aware dialogue generation. 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.