Understand the Machine Learning behind Chatbots
Bhavani Ravi (~bhavaniravi) |
Have you ever tried building a chatbot? You would definitely start with Dialogflow or IBM Watson or any chatbot framework from these tech giants. As you start building you be curious to understand what’s happening underneath these engines. When the use case hit the real world you will find the importance of understanding these inner workings.
In this talk, we will open the hood of an open-source chatbot framework RasaNLU and understand the components involved and how they contribute to building a chatbot
The talk is for someone who is curious about chatbot technologies and want to get a deeper understanding of how they work. A bit of python and a few ML beginner videos are enough to get you started building bots.
At the end of the talk, you will have an understanding of how chatbot engines work and how to tackle some of the challenges.
- Chatbot’s architecture (5 mins)
- What is Chatbot?
- Architecture - A flow Diagram, NLP, NLU
- Few Terminologies - Intent, Entities, Actions
- ML behind Chatbots (16 mins)
- Intent Classification - Given a text how does the chatbot understand whether it should search the DB or Greet back. (5 mins)
- Named Entity Extraction - Given a message, say “By me a pepperoni pizza” how does the chatbot know it has to buy “Pizza” and not pasta (5 mins)
- Processing pipelines - (5 mins)
- Q&A - 4 mins
Basic knowledge of Python
Built a basic chatbot
Has a curiosity to understand the internals of chatbot
Bhavani Ravi - Software Engineer - Orangescape - Tech Enthusiast - Django & Chatbot specialist - Mentor/Speaker Build2learn, Chennai Geeks.