Practical Natural Language Processing

Chapter 6. Chatbots

One machine can do the work of fifty ordinary men. No machine can do the work of one extraordinary man.

Elbert Green Hubbard

Chatbots are interactive systems that allow users to interact in natural language. They generally interact via text but can also use speech interfaces. Early 2016 saw the introduction of the first wave of chatbots that soon became ubiquitous. Platforms like Facebook Messenger, Google Assistant, and Amazon Alexa are some examples of chatbots. There are now tools that allow developers to create custom chatbots [1] for their brand or service so that consumers can carry out some of their daily actions from within their messaging platforms.

The introduction of chatbots into society has brought us to the beginning of a new era in technology: the era of the conversational interface. It’s an interface that soon won’t require a screen or a mouse to use. There will be no need to click or swipe; just the use of voice will be enough. This interface will be completely conversational, and those conversations will be indistinguishable from the conversations we have with our friends and family. Since chatbots deal with text under the hood, it’s all about understanding the text responses coming from users and producing reasonable replies. From understanding to generation, NLP plays a significant role, which we’ll see throughout this chapter.

The history of chatbots and of artificial intelligence in general are pretty intertwined. In the 1950s and ’60s, ...