Using a KG-Copy Network for Non-Goal Oriented Dialogues
This addresses the issue of generating well-grounded responses in non-goal oriented dialogues, particularly for soccer conversations, but is incremental as it builds on existing knowledge graph integration methods.
The paper tackles the problem of generating factually grounded responses in non-goal oriented dialogue systems by integrating knowledge graphs into the response generation process, proposing a novel neural network architecture and a new dataset in the soccer domain, with empirical results showing it outperforms state-of-the-art models.
Non-goal oriented, generative dialogue systems lack the ability to generate answers with grounded facts. A knowledge graph can be considered an abstraction of the real world consisting of well-grounded facts. This paper addresses the problem of generating well grounded responses by integrating knowledge graphs into the dialogue systems response generation process, in an end-to-end manner. A dataset for nongoal oriented dialogues is proposed in this paper in the domain of soccer, conversing on different clubs and national teams along with a knowledge graph for each of these teams. A novel neural network architecture is also proposed as a baseline on this dataset, which can integrate knowledge graphs into the response generation process, producing well articulated, knowledge grounded responses. Empirical evidence suggests that the proposed model performs better than other state-of-the-art models for knowledge graph integrated dialogue systems.