Towards Large-Scale Interpretable Knowledge Graph Reasoning for Dialogue Systems
This addresses the issue of rigid user interactions in voice assistants by improving reasoning scalability and interpretability, though it is incremental as it builds on existing transformer and knowledge graph techniques.
The paper tackles the problem of limited reasoning capabilities in dialogue systems by proposing a method that enables a transformer model to directly reason over a large-scale knowledge graph to generate responses, achieving effective and efficient incorporation with fully-interpretable paths.
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.