Dialogue as Collaborative Problem Solving

I will describe the current status of a long-term effort at developing dialogue systems that go beyond simple task execution models to systems that involve collaborative problem solving. Such systems involve open-ended discussion and the tasks cannot be accomplished without extensive interaction (e.g., 10 turns or more). The key idea is that dialogue itself arises from an agent’s ability for collaborative problem solving (CPS). In such dialogues, agents may introduce, modify and negotiate goals; propose and discuss the merits possible paths to solutions; explicitly discuss progress as the two agents work towards the goals; and evaluate how well a goal was accomplished. To complicate matters, user utterances in such settings are much more complex than seen in simple task execution dialogues and requires full semantic parsing. A key question we have been exploring in the past few years is how much of dialogue can be accounted for by domain-independent mechanisms. I will discuss these issues and draw examples from a dialogue system we have built that, except for the specialized domain reasoning required in each case, uses the same architecture to perform three different tasks: collaborative blocks world planning, when the system and user build structures and may have differing goals; biocuration, in which a biologist and the system interact in order to build executable causal models of biological pathways; and collaborative composition, where the user and system collaborate to compose simple pieces of music.