Chatbots, Theory and Practice

Very nicely done piece on Chatbots, and especially conversations that they claim to produce.  Non technical overview.

By Jonathan Mugan in Medium:
AI and machine learning. Co-founder and CEO at DeepGrammar, a startup specializing in NLP and deep learning. Author of The Curiosity Cycle.

Chatbots: Theory and Practice
There’s a lot of fluff surrounding chatbots, so I wrote this post to lay out the basics. I first review the theory of conversation to give us a sense of what we are aiming for. I then discuss three classes of chatbots. The simplest class is purposeless mimicry agents, which only provide the illusion of conversation. Members of this class include ELIZA and chatbots based on deep learning sequence-to-sequence models. The second and next most sophisticated class comprises intention-based agents such as Amazon’s Alexa and Apple’s Siri. These agents have a simple understanding and can do real stuff, but they generally can’t have multi-turn conversations. The third and most sophisticated class is conversational agents that can keep track of what has been said in the conversation and can switch topics when the human user desires.  .... " 

 I see that much of this is also covered in a Video.

See also DeepGrammar.com