An Approach to Inference-Driven Dialogue Management within a Social Chatbot
This addresses the problem of rigid and context-insensitive dialogue for users of social chatbots, though it appears incremental as it builds on existing symbolic and knowledge-based approaches.
The authors tackled dialogue management in social chatbots by modeling conversation as a collaborative inference process rather than a sequence of response generation tasks, resulting in a system that understands latent semantics, takes flexible initiative, and produces novel and coherent responses.
We present a chatbot implementing a novel dialogue management approach based on logical inference. Instead of framing conversation a sequence of response generation tasks, we model conversation as a collaborative inference process in which speakers share information to synthesize new knowledge in real time. Our chatbot pipeline accomplishes this modelling in three broad stages. The first stage translates user utterances into a symbolic predicate representation. The second stage then uses this structured representation in conjunction with a larger knowledge base to synthesize new predicates using efficient graph matching. In the third and final stage, our bot selects a small subset of predicates and translates them into an English response. This approach lends itself to understanding latent semantics of user inputs, flexible initiative taking, and responses that are novel and coherent with the dialogue context.