A chatbot is a service, powered by rules and sometimes artificial intelligence, that you interact with via a chat interface. The service could be any number of things, ranging from functional to fun, and it could live in any major chat product (Facebook Messenger, Slack, Telegram, Text Messages, etc.).
The popularity of chatbots is increasing, thanks to the gaining popularity of messaging platforms.Almost every large tech company has its own chatbot platform (Microsoft Bot Framework, Wit.ai, IBM Watson, etc.), but there are some open source projects such as the Rasa framework.
Rasa is the leading open source machine learning toolkit that lets developers expand bots beyond answering simple questions.It uses state-of-the-art machine learning models both in natural language processing and dialogue management.
The aim of the dissertation is to present the Rasa framework, and to create a student aid chatbot demo.
I present the data set recieved from the AUT department, on which I conducted data analysis, in order to determine the task of the chatbot.
In order to present Rasa’s full potential, I implemented a basic api to show how Rasa can interact with outside resources.
I created the Core and NLU machine learning models, and gave two alternative pipelines for the Natural Language Processing.
Finally, I integrated and tested the chatbot on the Facebook messenger platform.