Uploaded by Yigit Erdem Korkmaz

Introduction to Chatbots

Artificial Intelligence
Lecture 1
Prof. Oksana Pomorova
Office Room C11
A chatbot is programmed to work independently from a
human operator.
It can answer questions formulated to it in natural language
and respond like a real person. It provides responses based on
a combination of predefined scripts and machine learning
The most natural definition of a chatbot is – a developed a
program that can have a discussion/conversation with a
Chatbots are a channel opening up for customers (and
potentially employees) to interact with companies and/
or government organizations.
Since only text is available for interacting with the user,
the quality of the conversation is key.
of Chatbots
of Chatbots
Types of chatbots
Chatbots for entertainment and
Chatbots for business.
There are two major types of chatbots:
Chatbots for entertainment
Microsoft’s bots Xiaoice and Tay have similar behavior
Amazon’s Alexa, Apple Siri, or Microsoft’s Cortana….
First chatbot-psychotherapist ELIZA was introduced in
Business chatbots
Types of business chatbots
1. Support chatbot
2. Skills chatbot
3. Assistant chatbot
Types of business chatbots
1. Support chatbots
Support chatbots need to have personality, multi-turn
capability, and context awareness.
They should be able to walk a user through any major
business processes, and answer a wide range of FAQ-type
You will want to have a short-tail and long-tail combo
solution when building this type of chatbot.
Support chatbots are built to master a single domain, like
knowledge about a company.
Types of business chatbots
2. Skills chatbots
They should be able to follow commands quickly, so that your users
can multitask while engaging with the bot.
These chatbots do not need to worry too much about contextual
awareness, as people will quickly learn what to say, and say it
When building a skills bot, it is important to focus on integration,
especially when controlling a home or personalized objects.
Keep integration simple so your users can interact with the bot
without worrying about how to use.
They have set commands that are intended to make life easier: “Turn
on my living room lights,” for example.
Skills chatbots are typically more single-turn-type bots that do not
require a lot of contextual awareness.
Types of business chatbots
3. Assistant chatbots
Assistant chatbots need to be conversational and respond to
just about anything, while being as entertaining as possible.
Siri is a good example
When building an assistant chatbot, it is important to make it
as obvious as possible how the bot is trained. The range of
questions a user might ask is large, so making sure you have
adequate coverage is going to be the most difficult factor.
Assistant chatbots are more or less a middle ground between
the two bots (support and skills). They work best when they
know a little bit about a variety of topics.
Artificial Intelligence Markup Language is a simple
scripting language and the open standard for writing
Definition of intelligence
1a(1): the ability to learn or understand or to deal with new or
trying situations : REASONalso : the skilled use of reason
(2): the ability to apply knowledge to manipulate one's
environment or to think abstractly as measured by objective
criteria (such as tests)
c: mental acuteness : SHREWDNESS
bChristian Science : the basic eternal quality of divine Mind
b: information concerning an enemy or possible enemy or an area
also : an agency engaged in obtaining such information
3: the act of understanding : COMPREHENSION
4: the ability to perform computer functions
From Wikipedia, the free encyclopedia
Intelligence has been defined in many ways to include the
capacity for logic, understanding, selfawareness, learning, emotional_knowledge, reasoning, planning,
creativity, and problem solving.
It can be more generally described as the ability to perceive or
infer information, and to retain it as knowledge to be applied
towards adaptive behaviors within an environment or context.
Intelligence is most widely studied in humans but has also been
observed in both non-human animals and in plants.
Intelligence in machines is called artificial intelligence, which is
commonly implemented in computer systems using programs.
Artificial intelligence (AI),
sometimes called machine intelligence,
is intelligence demonstrated by machines, in contrast to
the natural intelligence displayed by humans and other
In computer science AI research is defined as the study of
"intelligent agents": any device that perceives its
environment and takes actions that maximize its chance of
successfully achieving its goals.[1]
What does intelligence mean in context to
We want the Chatbot to:
Recognize the intent of a sentence, ‘My bike is stolen’ relates to the
intent ‘Bicycle stolen’;
Identify and allow for typographical errors ‘Byke’ is ‘Bike’ and even cope
with language variants (the difference between US and UK English for
Detect the mood of the customer and provide related answers. “I DO
NOT AGREE” is different than “I do not agree ;-)”;
Understand the line in the context of a conversation E.g. following
the answer to a previous question such as “how do I do that?”
Realize that there is a difference between names and nouns – Jack
London is a proper noun / name and does not imply ‘Jack based out of
If possible relate to previous conversations with me as an end-user or
related customers
Intelligence for Chatbots is supported by
different capabilities such as:
A Chatbot’s response machine is the central engine where all
information is brought together,
Natural Language Processing (NLP) for understanding the intent of a
sentence, mood recognition, entity recognition (identifying the key
nouns and verbs);
Context recognition of a conversation (with a state machine for
predictive handling) to put a single line into a larger perspective.
Recognition has several degrees of complexity here. In the simplest
form it is a classification problem, but in the hardest form it a more
conventional NLP problem, grasping the semantics of something,
including the meaning of verbs, nouns and parts-of-speech (POS);
Intelligence for Chatbots is supported by different
capabilities such as:
History analytics to provide context from previous conversations (with the
same user or other users). This contains both conversations with the
same user as well as pattern recognition based on previous
conversations with all other users regarding the same topic – here is
where most people associate AI;
CRM, and specifically all previous interactions with the customer, such as
interactions via call centers, email, acquired products and complaints.
Knowing the customer will definitely help in understanding the conversation
and delivering right answers;
Event handling, events that are related to a conversation can intervene in
the conversation. This can be a single event or multiple events combined
together by Complex Event Processing for example a location update from
the device the user using to conduct the chat, or correlating chat content
across concurrent conversations for people in one area;
Intelligence for Chatbots is supported by
different capabilities such as:
The training model delivers the input for a supervised model, based
on which the NLP is able to determine the intent (or meaning) of the
sentence the customer delivers in the Chatbots.
Statistics, this is the most important capability used in the response
machine, NLP and the historical analysis.
We want to have:
A roadmap towards Intelligence
The above functionality is an ideal situation for the future
When looking at the levels shown in the maturity model, what
types of intelligence capabilities can be delivered with the different
Every level comes with a degree of complexity in order to deliver
the required intelligence.
Level 1
Chatbots with Level 1 intelligence support a low level of intelligence aimed at
supporting basic conversations
Often, these type of Chatbots are used in demos and can be used as wireframes for
mimicking intelligence features.
Similar to User Interface wireframes the implementation of the response system is
based upon ‘hard wired’ logic
The system can only understand predefined sentences that can be provided to the
end-user as menu entries
With the lowest level of complexity this level can be achieved in a short timeframe.
Level 2
By including line-based and context intelligence level 2 in intelligence maturity
is reached.
This enables end-user to communicate via their own language.
The response system tries to understand the intent of the lines and can
relate the intent to the entire conversation that takes place with the end-user.
The line based intelligence is supported by text analytical tooling.
This delivers a model that allows several NLP-related techniques to relate a
sentence to an intent.
Sentences that cannot be related to an intent, could be used as new input for
both training the model as well as making human adjustment to the model
Level 2
The complexity in a level 2 solution:
Find the right NLP tool or combination of tools. Different
Open Source packages are available for NLP, such as
Stanford NLP and Apache Open NLP, all with their specific
Secondly train the model to understand the conversation in
the best way. These training models can be industry specific,
so building upon an already available industry specific training
model will definitely improve the quality of the conversation.
Determine the context, what state model can support the
conversation and what information should be stored during the
Level 3
In order to reach level 3 intelligence, the response system needs to be
enriched with information about the end-user included in the conversation
(CRM) and historical analysis based upon previous conversations with
the end-user, but also previous conversations with different users.
Thus historical analysis can be divided into two categories, manual analysis
and Machine Learning.
Analytics data can be manually analyzed and fed into the training model.
Or develop a machine learning module which continuously enhance and
extend the training model.
Level 3
The response system is fed with information from NLP, Content, History
and CRM and determines, with growing confidence, the best answer
towards the end-user.
The Context part in this solution is extended to store all relevant
information coming from disparate sources.
Level 3
The complex part in this solution is the way the Chatbot response
system combines all information from NLP, Context, Training models,
CRM and History analytics is combined and processes this information
into an answer with the highest likelihood.
The choice for a statistical model, supporting the Chatbot response
system, is crucial.
The Chatbots Intelligence area
The Chatbot response system, responsible for determining the
best answer related to the question the end-user entered, is
dependent on multiple information sources and a high quality
statistical model supported by data mining algorithms.
Open Source tooling, industry models and statistical models are
available but it is the choice for the right combination that makes a
difference in the response quality.
The Intelligence maturity model helps to manage the expectations
of what can be expected from the Chatbot.
A four-time winner of the prestigious Loebner
Prize Turing Test, Mitsuku is widely considered
the world's best, most humanlike, conversational
chatbot. She has been featured by the Wall Street
Journal, BBC, Guardian, and Wired, and
converses with millions of people monthly on
channels like Messenger, Kik, and the web
Via various third-party integrations and partners,
Mitsuku is also available as a fully conversational
character. The avatar runs on mobile and mobile
AR, and live-streams autonomously onTwitch TV
The Mitsuku codebase can be licensed, along
with other modules, from Pandorabots and
incorporated into other chatbot applications.