Incremental understanding in human-computer dialogue and experimental evidence for advantages over nonincremental methods

Current dialogue systems generally operate in a pipelined, modular fashion on one complete utterance at a time. Converging evidence shows that human understanding operates incrementally and makes use of multiple sources of information during the parsing process, including traditionally “later” aspects such as pragmatics. We describe a spoken dialogue system that understands language incrementally, gives visual feedback on possible referents during the course of the user’s utterance, and allows for overlapping speech and actions. We present findings from an empirical study showing that the resulting dialogue system is faster overall than its nonincremental counterpart. Furthermore, the incremental system is preferred to its counterpart – beyond what is accounted for by factors such as speed and accuracy. These results are the first to indicate, from a controlled user study, that successful incremental understanding systems will improve both performance and usability.