Automated systems are not yet able to engage in a robust dialogue with users due the complexity and ambiguity of natural language. However, humans can easily converse with one another and maintain a shared history of past interactions. In this paper, the researchers introduce Chorus, a system that enables realtime, two-way natural language conversation between an end user and a crowd acting as a single agent. Chorus is capable of maintaining a consistent, on-topic conversation with end users across multiple sessions, despite constituent individuals perpetually joining and leaving the crowd. This is enabled by using a curated shared dialogue history.
The researchers have presented Chorus, a system that allows two-way dialogue between a user and the crowd. Chorus allows the crowd to have one voice, as if it were a single individual, instead of burdening the user with managing multiple lines of conversation or limiting the interaction to use only oneway communication. They demonstrated that the crowd could not only maintain a consistent conversation with users, but also learn and remember over the course of both single and repeated interactions.
SOURCE : http://hci.cs.rochester.edu/pubs/pdfs/chorus_demo.pdf