Regardless of which type of classifier is used, the end-result is a response. Like a music box, there can be additional “movements” associated with the machinery. A response can make use of external information (like weather, a sports score, a web lookup, etc.) but this isn’t specific to chatbots, it’s just additional code. A response may reference specific “parts of speech” in the sentence, for example: a proper noun. Also the response (for an intent) can use conditional logic to provide different responses depending on the “state” of the conversation, this can be a random selection (to insert some ‘natural’ feeling).
Back to our earlier example, if a bot doesn’t know the word trousers and a user corrects the input to pants, the bot will remember the connection between those two words in the future. The more words and connections that a bot is exposed to, the smarter it gets. This process is similar to that of human learning. Our capacity for memory and synthesis is part of what makes us unique, and we’re teaching our best tricks to bots.
In 1950, Alan Turing's famous article "Computing Machinery and Intelligence" was published,[7] which proposed what is now called the Turing test as a criterion of intelligence. This criterion depends on the ability of a computer program to impersonate a human in a real-time written conversation with a human judge, sufficiently well that the judge is unable to distinguish reliably—on the basis of the conversational content alone—between the program and a real human. The notoriety of Turing's proposed test stimulated great interest in Joseph Weizenbaum's program ELIZA, published in 1966, which seemed to be able to fool users into believing that they were conversing with a real human. However Weizenbaum himself did not claim that ELIZA was genuinely intelligent, and the introduction to his paper presented it more as a debunking exercise:
×