bot2bot (2017)
web, electronics, projector
How do we train computational systems to understand human conversation?
Truly understanding how to hold conversation is a part of life that feels second nature. Regardless of conversational aptitude, most humans are able to hold a basic conversation and at least have small talk with one another.
Despite its seemingly mundane qualities, conversation is complex and can be a delicate dance between two or more individuals. The study of conversational analysis is a testament to the complexity at which humanity operates. Its literature shows that humans in practice are not as eloquent or clear as dialog in literature or modern-day cinema, yet mutual understanding is still achieved.
How do we embed a sense of conversational understanding and capabilities within computational systems?
bot2bot is a piece that explores the state-of-the-art in designing conversational systems. Leveraging the Watson Conversation Platform, the piece puts one robust conversational agent against another as a way of switching the perspective on our experience with chatbots, voice agents and the like. In current manifestations of conversational agents, humans are active participants. However, in bot2bot the role of the human is that of a spectator. From this perspective, one can follow the dialog the elapses between the two agents and discover not only gaps in understanding but also witness a new form of conversation—the uncanny valley of computational conversation.