No abstract

In this demonstration we present a mixedinitiative dialog system for address recognition that lets users to specify a complete addresses in a single sentence with address components spoken in their natural sequence. Users can also specify fewer address components in several ways, based on their convenience. The system extracts specified address components, prompts for missing information, disambiguates items independently or collectively all the while guiding the user so as to obtain the desired valid address. The language modeling and dialog management techniques developed for this purpose are also briefly described. Finally, several use cases with screen shots are presented. The combined system yields very high task completion accuracy on user tests.

No abstract