Welcome to the second episode of OpenDialogues, the podcast hosted by Maaike Coppens and Ronald Ashri discussing everything Conversation Design and OpenDialog.
Language understanding is hard. This is perhaps the most crystal clear lesson of the past few years of intensified efforts across the world to build conversational applications. It’s no wonder that in that historic document from 1955, introducing the first
Yesterday, at Google I/O there was a particularly relevant announcement for us. Google introduced LaMDA. A Language Model for Dialogue Applications. LaMDA builds on work they’ve done in the past that was introduced under the name Meena. Glad to see
Conversational applications are going to redefine how we interact with machines and access services. From the essentials, like health, education and social care to the less essential, like picking a new pair of shoes or our next vacation, conversational apps
After a couple of years helping clients design and deploy conversational applications (using a variety of existing tools) we realised that something fundamental was missing. Where was the conversational model in conversational design and tooling? So I reached back into my academic AI days and the field of multi-agent research for some help and inspiration. The result is OpenDialog.
The Conversational AI challenge is typically framed as a natural language understanding (NLU) through machine learning (ML) type of problem. Is that, however, all there is to it? At OpenDialog we think that there is a broader viewpoint that subsumes the NLU challenge and provides us with more tools to build effective Conversational AI applications.
Words matter. They frame our thinking and influence our decisions.
