Human-like Communication
The most famous grand challenge for machine intelligence is human-like communication. This chapter explores two problem that need to be solved in order for machines to meet this challenge. The first is the technical difficulties posed by ordinary conversation. Production and comprehension in conversation are: multimodal, multi-person, incremental, concurrent, and jointly managed. The fine-grained complexity of these aspects of human interaction are beyond the current state of the art but should, ultimately, be tractable. The second set of problems are foundational. Models that assume human communication is underwritten by a shared language are unable to account for the ubiuquitous and systematic role misunderstanding plays in everyday interaction. As a result they also fail to explain how people adapt their language use to each new person and new situation in real time. This capability is essential for any machine that aims to engage constructively with human diversity.