Back to the Future for Dialogue Research: A Position Paper

This short position paper is intended to provide a critique of current approaches to dialogue, as well as a roadmap for collaborative dialogueresearch. It is unapologetically opinionated, but informed by 40 years of dialogue research. No attempt is made to be comprehensive. The paper will discuss currentresearch into building so-called "chatbots", slot-filling dialogue systems, and plan-based dialogue systems. Forfurther discussion of some of these issues, please see (Allen et al., in press). The currently dominant approach to building dialogue systems, particularlythose commonly referred to as "chatbots", is to train a neural network-based system "end-to-end" based on a large corpus of human-human dialogues, potentially supplementedwith other information.