DialPort: Connecting the Spoken Dialog Research Community to Real User Data
This addresses the problem of limited real-world data access for the spoken dialog research community, though it is incremental as it builds on existing portal and integration concepts.
The paper introduces DialPort, a portal that connects academic spoken dialog systems to real user data, and demonstrates its integration with systems like Cambridge University's multi-domain dialog system and external APIs such as NOAA weather and Yelp.
This paper describes a new spoken dialog portal that connects systems produced by the spoken dialog academic research community and gives them access to real users. We introduce a distributed, multi-modal, multi-agent prototype dialog framework that affords easy integration with various remote resources, ranging from end-to-end dialog systems to external knowledge APIs. To date, the DialPort portal has successfully connected to the multi-domain spoken dialog system at Cambridge University, the NOAA (National Oceanic and Atmospheric Administration) weather API and the Yelp API.