Guiding Dialogue Agents to Complex Semantic Targets by Dynamically Completing Knowledge Graph

Abstract

In target-oriented dialogue, the representation and achievement of targets are two interrelated essential issues. In current approaches, the target is typically assumed to be a single object represented as a word, which makes it relatively easy to achieve through dialogue with the help of a knowledge graph (KG). However, when the target has complex semantics, the existing KG is often incomplete in tracking semantic relations. This paper studies target-oriented dialog where the target is a topic sentence. We combine the methods of knowledge retrieval and relationship prediction to construct a context-related dynamic KG, in which we can track the implicit semantic paths in the speaker's mind that may not exist in the existing KGs. In addition, we also designed a novel metric to evaluate the tracked path automatically. The experimental results show that our method can control the agent more logically and smoothly toward the complex target.