Rise above archaic tech with the use of ML, NLP, and BOTS ! Part 3— BOTS
What is it?
A bot is an application that performs an automated task, such as setting an alarm, telling you the weather or searching online. If you own an iPhone you already have a bot installed, Siri. If you’re on Windows, Cortana is ready for your service. It’s like a service that you can interact to using your language. Apps as we know them today is static in the way you have some set controls, in contrast with bots where you are just having a conversation.
If you think that every bot needs to be super smart and humanoid like Siri, your wrong. Most of them must be fast and effortless in terms of which service they provide.
Why?
Bots have been around since the dawn of the internet, so why haven’t they gained more traction already? Well, bots are getting smarter with the use of state-of-the-art machine learning and cutting-edge natural language processing. Bots are far superior to primitive humans when it comes to certain areas.
Also, the big players are putting in a lot of resources into bots. Especially Facebook, Microsoft, Slack, Kik, and Telegram. Even the US government have its own bot. Some believe people are tired of apps and would rather have bots. That is not proven to be true yet, but their popularity sure is rising.
In the future, there are a probability that every business is going to have a bot. A bot for company information, sales and other. It is immensely fast to get going with a bot, arguably faster than mobile apps and even websites. It is also super easy to use. Our language is the user interface in the bots.
To design a conversational interface vs an application interface is quite different. They do still have some problems but this way of interacting with a service will take a few years before taking off. We still need apps though. There are however many compelling reasons that bots will make a pretty great impact in the few years.
Frameworks
Microsoft Bot Framework
Microsoft Bot Framework is an easy and great way of starting developing bots using your existing knowledge in C# and the .NET universe. You use the bot template to get started and its development is quite similar to developing an ASP NET Web API.
LUIS AI
A machine learning-based service to build natural language into apps, bots, and IoT devices. Quickly create enterprise-ready, custom models that continuously improve.
LUIS is a great service from Microsoft to use for the machine learning and natural language part in your bot. With LUIS you can create your own model or use a prebuilt one. Microsoft bot framework works well with LUIS. They have full support for American English as well as Chinese. There are however a range of languages that supports phrase suggestions. Check out the list of the supported languages. LUIS have a free tier where you can have up to 10 000 API calls.
Where can you learn more about BOTS?
Pluralsight have a neat course about Microsoft Bot Framework and LUIS. Botnerds is a site with extensive articles on all bots related. If you are interested in creating a bot for Telegram, check out their article. There are also a ton of high quality articles on the matter here on Medium. Good luck and have fun learning about bots!
This was part 3 and final part of a series about machine learning, natural language processing and bots. Hold that clap button if you enjoyed this article.
