PyConf Hyderabad 2017

This talk will show you how you could use open-source tools to build a chatbot without handing your data over to third parties (Facebook/Microsoft/Google,etc.)

You will learn:

• how a chatbot works behind the scene
• how to transfer knowledge to a chatbot
• how to build a production-ready bot which you would own completely
• how to use Socket.IO to allow real-time communication with your chatbot.

Outline

• Introduction: motivations for building your bot in-house
• Chatbot architecture.
• Understanding the components of chatbot -
  • Natural Language Understanding (NLU)
    • Intent Classification
    • Entity Extraction
  • contextual dialogue management using Finite State Machines (FSM)
  • Response Generation
  • Knowledge Base
• How to use Open Source Tools to build your own chatbot:
  • Rasa.AI (having configurable backends like spacy/sklearn/mitie) - to build intent & entity extraction.
  • Transitions - to build a context manager using FSMs.
  • ChatterBot - to generate automated response based on historical conversation.
  • Socket.IO - to build a real-time communication system.
• Demo

Requirements

Basic knowledge of NLP and Machine Learning.
Basic understanding of Finite State Machines.
Familiarity with Python.

Speaker bio

Saikat Kumar Dey - I am a Data Scientist at Endurance International Group. I have been working on building a conversational assistant for Customer Support in my company. I have worked on customer segmentation & retention efforts in the past.

Parth Savjani - Associate Data Scientist at Endurance International Group India
More than 3 years of experience working with Data related field ranging from Data-warehouse to predictive modelling on transaction data, postgraduate from IIIT Bangalore with Data Science major.

Links

• Personal website: http://saikatkumardey.com
• Medium: https://medium.com/@saikatkumardey
• Twitter: https://twitter.com/deysaikatkumar
• Github: https://github.com/saikatkumardey/
• LinkedIn: https://www.linkedin.com/in/saikatkumardey/
• LinkedIn: https://www.linkedin.com/in/parthsavjani/

Slides

https://docs.google.com/presentation/d/1Et9u08KFc-O5vhU9PNrEWqFGKsEGpD9QKbe5-RIbGFY/edit?usp=sharing