What are Chatbots?
Chat bots are computer programs that mimic conversation with people using artificial intelligence. They can transform the way you interact with the internet from a series of self-initiated tasks to a quasi-conversation.
The Kik Bot Store is launching with 16 bots, including the Weather Channel, H&M, Vine and Funny or Die. But the open platform will allow developers to add their own, as long as they comply with Kik’s teen-centric standards (no porn allowed), so expect more soon.
Without a chat bot, a user might direct his browser to weather.com, then type in their zip code to get the forecast. With the Kik’s Weather Channel bot, a user can send a chat asking for “Current Conditions” or a “3-Day Forecast” and the bot will reply with your answer.
How Chatbots Work
There are two types of chatbots, one functions based on a set of rules, and the other more advanced version uses machine learning.
Chatbot that functions based on rules:
This bot is very very limited. It can only respond to very specific commands. If you say the wrong thing, it doesn’t know what you mean.
This bot is only as smart as it is programmed to be.
Chatbot that functions using machine learning:
This bot has an artificial brain AKA artificial intelligence. You don’t have to be ridiculously specific when you are talking to it. It understands language, not just commands.
This bot continuously gets smarter as it learns from conversations it has with people.
Bots are created with a purpose. A store will likely want to create a bot that helps you purchase something, where someone like Comcast might create a bot that can answer customer support questions.
The model for the intelligent chatbot?
A chatbot based on the retrieval-based model works on the concept of predefined responses. The chatbot picks appropriate responses from the repository stacked which is based on the context and query raised by the user. Generative models built using machine translation techniques come with the ability to generate new responses right from the word go. Generative models enable longer conversations where the chatbot deals with several user queries. Though deep learning techniques are leveraged for building both these models, generative models seem to draw more power than its counterpart.