Towards Large-Scale Interpretable Knowledge Graph Reasoning for Dialogue Systems

TL;DR

This paper introduces a scalable transformer-based approach enabling dialogue systems to perform reasoning over large knowledge graphs, improving response generation and interpretability in conversational AI.

Contribution

It presents the first transformer model capable of reasoning over differentiable knowledge graphs for dialogue response generation, enhancing scalability and interpretability.

Findings

Effective reasoning over large knowledge graphs in dialogue systems

Improved response quality with interpretable reasoning paths

Applicable to both task-oriented and chit-chat dialogues

Abstract

Users interacting with voice assistants today need to phrase their requests in a very specific manner to elicit an appropriate response. This limits the user experience, and is partly due to the lack of reasoning capabilities of dialogue platforms and the hand-crafted rules that require extensive labor. One possible way to improve user experience and relieve the manual efforts of designers is to build an end-to-end dialogue system that can do reasoning itself while perceiving user's utterances. In this work, we propose a novel method to incorporate the knowledge reasoning capability into dialogue systems in a more scalable and generalizable manner. Our proposed method allows a single transformer model to directly walk on a large-scale knowledge graph to generate responses. To the best of our knowledge, this is the first work to have transformer models generate responses by reasoning over differentiable knowledge graphs. We investigate the reasoning abilities of the proposed method on both task-oriented and domain-specific chit-chat dialogues. Empirical results show that this method can effectively and efficiently incorporate a knowledge graph into a dialogue system with fully-interpretable reasoning paths.