2. What is a CHATBOT?
• A chat robot, a computer program
that simulates human conversation,
or chat, through artificial intelligence.
• It is a service, powered by rules and
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).
3. List of best Known
Chatbots:
• ELIZA & PARRY
• A.L.I.C.E
• Mitsuku (Leobner Prize
Winner) - Prize in AI for
Chatbots in 2013
• Jabberwacky
• PersonalityForge
• Botser
• Cleverbot
5. Why Would You Need
Chatbot?
• Saves cost of hiring human employees.
• 24/7 Deployment
• Immune to stress, boredom and
sickness.
• Doesn’t misbehave.
• Handles multiple (millions) consumers
simultaneously.
• Replies in natural language.
• No need to install an additional
application.
• Very fast response time.
6. Types of Chatbot
• RETRIEVAL-BASED MODELS -
• Uses a repository of predefined responses and some kind
of heuristic to pick an appropriate response based on the
input and context.
• The heuristic could be as simple as a rule-based
expression match, or as complex as an ensemble of
Machine Learning classifiers.
• GENERATIVE MODELS
• 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.
7. Open Domain vs. Closed
Domain Conversations
• In an open domain setting, the user
can take the conversation anywhere.
There isn’t necessarily have a well
defined goal or intention. Ex:
Conversation about refinancing one’s
mortgage
• In a closed domain setting, the space
of possible inputs and outputs is
somewhat limited because the
system is trying to achieve a very
specific goal. Ex : Hotel’s Customer
Support or Shopping Assistants
8. Long vs Short
Conversations
• The longer the conversation the more difficult to
automate it because it need to keep track of
what has been said.
• Ex: Customer support conversations.
• Short-Text Conversations where the goal is to
create a single response to a single input.
• Ex: What is your name?
9. Retrieval Based
Model
• The vast majority of production
systems today are retrieval-
based, or a combination of
retrieval-based and generative
model.
• Generative models are an active
area of research, but we’re not
quite there yet.
• For building Hotel’s Customer
Support, right now best bet is
most likely a retrieval-based
model.
12. Deep Learning Models for Chatbots
• One of the Deep Learning model for building chatbot is called
a Dual Encoder LSTM network.
• There are many Deep Learning architectures – it’s an active
research area.
• seq2seq model often used in Machine Translation would
probably do well on this task.
• tf-idf predictor
• tf-idf stands for “term frequency – inverse document”
frequency and it measures how important a word in a
document is relative to the whole corpus.
• Documents that have similar content will have similar
tf-idf vectors.
• o Intuitively, if a context and a response have similar
words they are more likely to be a correct pair.
13. Popular Chatbot Platforms
• Microsoft Bot Framework
• Chat Fuel
• Google Dialog Flow
• IBM Watson Conversation
14. Usecases
• Help Desk Automation
• Password Resets
• FAQs
• Basic Tech-Support
• Registrations
• Token Distributions
• Psychology Assessment
• Realtime psychological and psycho-analytical assessments.
• Higher rates of accuracy
• Large number of patients can be screened
• Lower cost of diagnosis
• Can help in preventing bullying and suicides
• Concierge Service
• Smart Home Automation Control