This chapter covers
- Understanding four chatbot approaches
- Finding out what Artificial Intelligence Markup Language is all about
- Understanding the difference between chatbot pipelines and other NLP pipelines
- Learning about a hybrid chatbot architecture that combines the best ideas into one
- Using machine learning to make your chatbot get smarter over time
- Giving your chatbot agency—enabling it to spontaneously say what’s on its mind
We opened this book with the idea of a dialog engine or chatbot NLP pipeline because we think it’s one of the most important NLP applications of this century. For the first time in history we can speak to a machine in our own language, and we can’t always tell that it isn’t human. Machines can fake being human, which is a lot harder than it sounds. There are several cash prize competitions, if you think you and your chatbot have the right stuff: