This presentation includes - History, Functions, Working, Advancement, Applications, Advantages, Disadvantages, Limitations & Contests Held - of Chatbot Technology.

1. COLLOQUIUM
CS14.371
CHATBOT TECHNOLOGY

2. PRESENTED TO:- Presented By:-
AISHWARYA BHARDWAJ
2

3. ABSTRACT
• A chatbot is a computer program that simulates human
conversation through voice commands or text chats or
both. Chatbot, short for chatterbot, is an Artificial
Intelligence (AI) feature that can be embedded and used
through any major messaging applications. There are a
number of synonyms for chatbot, including "talk-bot,"
"bot," "interactive agent" or "artificial conversation
entity."
3

4. TABLE OF CONTENTS
INTRODUCTION:CHATBOT…………………………………….. 5
AI & NLP…………………………………………………………….. 6
TYPES OF CHATBOTS……………………………………………. 7
HISTORY……………………………………………………………. 8
FUNCTIONS………………………………………………………... 11
WORKING: CHATBOTS………………………………………….. 12
ADVANES: CHATBOT TECHNOLOGY………………………… 13
APPLICATIONS……………………………………………………. 16
ADVANTAGES OF CHATBOTS………………………………….. 17
DISADVANTAGES OF CHATBOTS……………………………... 19
LIMITATIONS OF CHATBOTS………………………………….. 20
CHATBOT DEVELPOMENT SITES…………………………….. 21
CONTESTS HELD………………………………………………… 25
CONCLUSION…………………………………………………… 26
REFERENCES…………………………………………………… 27 4

5. TABLE OF FIGURES
• Fig.1 Working Of Chatbots…………………………… 13
• Fig.2 Chatbot Usage In Different Domains…………………. 24
• Fig.3 Predicted Use Cases For Chatbots …..……………. 25
5

6. INTRODUCTION: CHATBOT
• A chatbot is an artificial intelligence (AI) software that
can simulate a conversation (or a chat) with a user in
natural language through messaging applications,
websites, mobile apps or through the telephone.
• A chatbot is often described as one of the most advanced
and promising expressions of interaction between humans
and machines.
• However, from a technological point of view, a chatbot
only represents the natural evolution of a Question
Answering system leveraging Natural Language
Processing (NLP). 6

7. ARTIFICIAL INTELLIGENCE (AI):-
• A branch of computer science dealing with the simulation of
intelligent behaviour in computers.
• The capability of a machine to imitate intelligent human
behaviour.
NATURAL LANGUAGE PROCESSING (NLP):-
Natural language processing (NLP) is the ability of a computer
program to understand human language as it is spoken. NLP is
a component of artificial intelligence (AI).
7

8. TYPES OF CHATBOTS
• Chatbots based on Artificial Intelligence (AI):
These chatbots learn dynamically, and are constantly being updated
through interactions with customers. They are intelligent, with an
advanced design and offer a very positive UX.
• Fixed Chatbots:
These are programs with fixed information, which offer limited help.
They are used for customers with limited access to Customer
Service, or to solve repetitive questions. They are not as popular, as
they are unable to understand human behaviour. In addition, if any
questions arise beyond those they have established, you will not be
able to answer them.
8

9. HISTORY
• The term "ChatterBot" was originally coined by Michael Mauldin
(creator of the first Verbot, Julia) in 1994 to describe these
conversational programs.
• Though chatbots are still in their relative infancy technologically,
they have existed for decades. One of the first chatbots, ELIZA,
was developed in 1966 by computer scientist Joseph Weizenbaum
at the MIT Artificial Intelligence Laboratory.
• Joseph designed ELIZA to mimic human interaction through
pattern recognition; ELIZA could not, however, react to queries in
their full context. Instead, ELIZA had built-in scripts that allowed
it to display the illusion of intelligence in answering questions on
a given subject, such as those related to psychological evaluation.
9

10. • PARRY was an early example of a chatterbot, implemented in
1972 by psychiatrist Kenneth Colby.
• While ELIZA and PARRY were used exclusively to simulate
typed conversation, many chatbots now include functional
features such as games and web searching abilities.
• More recent notable programs include A.L.I.C.E., Jabberwacky
and D.U.D.E (Agence Nationale de la Recherche and CNRS
2006).
• A.L.I.C.E. is still purely based on pattern matching techniques
without any reasoning capabilities, the same technique ELIZA
was using back in 1966.
10

11. • Jabberwacky learns new responses and context based on
real-time user interactions, rather than being driven from a
static database.
• Today, most chatbots are accessed via virtual assistants such
as Google Assistant and Amazon Alexa, via messaging apps
such as Facebook Messenger or WeChat, or via individual
organizations' apps and websites.
11

12. “One should not look at a chatbot as a simple
messaging service.
Chatbots today are designed to not only perform natural
language understanding but are also able to perform
cognitive service functions such as:
• Speech to Text
• Computer Vision
• Language Recognition and Translation
• Content Moderation
• Speaker Recognition
• Text Analytics
12

13. WORKING OF CHATBOT
13
Fig.1[1]

14. Advances In Chatbot Technology
• Microsoft has recently demonstrated one of their more advanced
ChatBots over in China, Xiaolce, which is said to have more
natural interaction with humans demonstrating Microsoft’s
determination to get ahead in the ChatBot world.
• The knowledge which has been implemented in these new and
more advanced ChatBots is called ‘Full Duplex Voice Sense’,
which means two-way communication can be had. In other
words, the Microsoft Xiaolce is a telephone whereas the Alexa
is a walkie-talkie.
14

15. • Automated Call Centers with AI technology
With the advancement done in NLO as mentioned above-automated
call centers will soon come into existence. Combining NLO, AI
voice generation and ‘server-less’ technology will allow automated
call centers. Automated call centers will have deep domain
knowledge and this will help to have a conversation with the
customers.
• Deep Customer Insights
Chatbots easily store customer data as per request which can be
easily retrieved to make a proper analysis.
15

16. Chatbots assure
• Logical,
• Transparent, and
• Clear Communications.
You will have them directly inside your applications, and
regardless of what you speak will get recorded. In this way,
there’s no possibility of ambiguities or disarray.
• As per the latest analysis, just 20 percent of the web
clients have followed the chatbot usage in their daily
subsistence which is estimated to raise in the future up to
93 percent till 2021.
16

17. APPLICATIONS:-
• Messaging apps
• As part of company apps and websites
• Chatbot sequences
• Company internal platforms
• Banking
• Politics
• Toys
17

18. Advantages: Chatbot Technology
• Save Time
For instance, when used on your website they can provide fast,
automated answers to most questions. Their use prevents customers
from waiting a day or longer to receive responses as they would have
in the past.
• Save Money
Chatbot use can be cheaper than hiring more workers. Costs to have a
chatbot built can range from 2K to 10K or more depending on the
complexity needed.
• Provide Greater Customer Satisfaction
Chatbots don’t work 8 hour days and don’t need sleep which means they are
always available. Frustrated customers who don’t get quick answers, on the
other hand, may leave your website and never return. Chatbots can eliminate
that scenario and help you keep your customers.
18

19. • Increase Customer Base
They may help you reach more people which can increase your
customer base. Since chatbots can be used in many applications you
can take advantage of that to help your business grow.
• Cut Down on Errors
Unfortunately, humans handling customer service questions and other
issues can make errors. They can forget things, transpose numbers, and
make other types of mistakes. Not so with chatbots.
• Add Good Humor
You never have to worry about a chatbot being in a bad mood. They
will never turn away customers with an angry response, attitude, or
glance. They can be programed to have a bit of humor which can make
them seem more humanlike.
19

20. Disadvantages: Chatbot Technology
• Complex interface
• They don’t get you right
• Time-consuming
• Installation cost
• Null decision making
• Bad memory
• Your personnel information is being stored & can be
misused.
• People will become dependent and will be vulnerable.
20

21. LIMITATIONS OF CHATBOTS
It have some important limitations in terms of functionalities
and use cases:-
• As the database, used for output generation, is fixed and
limited, chatbots can fail while dealing with an unsaved
query.
• A chatbot's efficiency highly depends on language processing
and is limited because of irregularities, such as accents and
mistakes that can create an important barrier for international
and multi-cultural organisations.
21

22. Chatbot Development Sites
The process of building, testing and deploying chatbots can be done on
cloud-based chatbot development platforms offered by cloud Platform
as a Service (PaaS) providers such as:-
• Oracle Cloud Platform
• SnatchBot
• IBM Watson
• These cloud platforms provide Natural Language Processing,
Artificial Intelligence and Mobile Backend as a Service for chatbot
development.
• Some Companies like Microsoft Azure and AARC are currently
providing their Bot Engines through which chatbot Platforms or
Software can be developed.
22

23. • Chatbots are unable to deal with multiple questions at the
same time and so conversation opportunities are limited.
• As it happens usually with technology-led changes in
existing services, some consumers, more often than not
from the old generation, are uncomfortable with chatbots
due to their limited understanding, making it obvious that
their requests are being dealt machines.
23

24. Chatbot Usage In Different Domains
24
Fig.2[2]

25. Fig.3[3] 25

26. CONTESTS HELD
Two such annual contests are:-
• The Loebner Prize
• The Chatterbox Challenge (the latter has been offline
since 2015, however materials can still be found from
web archives).
26

27. CONCLUSION
Chatbots for business will definitely evolve in the following
years – the design and architecture can possibly improve to a
point where interactive bots become the standard for
customer service. Still, there are different apps for Chatbots
across a variety of sectors.
In the end, the adaptation of a new technology largely
depends on these factors:
• - Lower costs
• - Growing demand
• - Improved technology
27

28. REFERENCES
• https://www.investopedia.com/terms/c/chatbot.asp
• https://en.wikipedia.org/wiki/Chatbot
• https://www.expertsystem.com/chatbot/
• https://www.searchenginejournal.com/future-of-chatbots/278595/
• https://due.com/blog/chatbots-business-benefits/
• https://www.ecommerce-nation.com/chatbots-advantages-and-disadvantages-of-
these-tools/
• https://www.esparkinfo.com/latest-chatbots-trends-in-2019.html
• https://www.kdnuggets.com/2017/01/grakn-year-review-chatbot-
technologies.html
• https://www.grandviewresearch.com/static/img/research/us-chatbot-market.png
• http://assets.media-marketing.com/wp-content/uploads/2019/02/medijski-trend-
2019-svetla-buducnost-za-cetbotove.png
• https://acquire.io/blog/chatbots-trends/
• [1] https://www.workingofchatbots/images/Chatbotso
• [2] https://.chatbotusageindifferentdomains/images/Chatbo
• [3] https://www.predictedusecasesofchatbot/images/Chatbo
28

29. THANK YOU
29