Knowledge Aware Conversation Generation with Explainable Reasoning over Augmented Graphs
This work addresses the problem of generating more informed and explainable conversations for AI chatbots, though it is incremental as it builds on existing methods by integrating graph and text knowledge.
The paper tackles the challenge of fusing knowledge graphs and texts for open-domain conversation generation by proposing a system with an augmented graph, knowledge selector, and response generator, achieving improved performance on two datasets compared to state-of-the-art models.
Two types of knowledge, triples from knowledge graphs and texts from documents, have been studied for knowledge aware open-domain conversation generation, in which graph paths can narrow down vertex candidates for knowledge selection decision, and texts can provide rich information for response generation. Fusion of a knowledge graph and texts might yield mutually reinforcing advantages, but there is less study on that. To address this challenge, we propose a knowledge aware chatting machine with three components, an augmented knowledge graph with both triples and texts, knowledge selector, and knowledge aware response generator. For knowledge selection on the graph, we formulate it as a problem of multi-hop graph reasoning to effectively capture conversation flow, which is more explainable and flexible in comparison with previous work. To fully leverage long text information that differentiates our graph from others, we improve a state of the art reasoning algorithm with machine reading comprehension technology. We demonstrate the effectiveness of our system on two datasets in comparison with state-of-the-art models.