Coherent Topic Transition in a Conversational Agent

A conversational agent for entertainment and engagement requires the ability to maintain coherent conversations. We describe the use of semantic relatedness to select the next conversational fragment that an agent utters, to maximise dialogue coherence and/or to suggest new directions for a dialogue. We compare our approach, using a specific semantic relatedness metric, to an existing nearest-context mechanism based on TF × IDF for selecting fragments to continue a conversation. Evaluation with human judges shows that use of semantic relatedness provides improved coherence across a sample collection of generated conversations.