Using a KG-Copy Network for Non-Goal Oriented Dialogues

TL;DR

This paper introduces a neural network model that integrates knowledge graphs into non-goal oriented dialogue systems, improving the generation of factually grounded responses in a soccer domain dataset.

Contribution

It proposes a novel neural network architecture for end-to-end knowledge graph integration in dialogue generation, along with a new soccer dialogue dataset with associated knowledge graphs.

Findings

Model outperforms state-of-the-art knowledge graph dialogue systems.

Provides a new dataset for soccer-related non-goal oriented dialogues.

Demonstrates effective grounding of responses with factual knowledge.

Abstract

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.