One of the best tools Microsoft currently has in its AI toolkit is the QnA Maker. It uses NLP to mine one or more source documents and expose the contents as a chatbot. It does a great job of answering, but a newly added feature (Multi-Trun) mimics a crucial ability that a real human adds: the ability to clarify, ask for more information, or do anything more than a one-off question-response type of conversation.
In this article, Matt Wade examines this feature and how to exploit it to make your QnA bots even smarter.
But that all changed with the recent introduction of QnA Maker multi-turn conversations. With multi-turn, the experience with your QnA KB is much more fluid and significantly more natural. Let’s see how.