Introduction to AI Chatbots
Aishwarya Gupta
Department of Computer Science Divya Hathwar
Dayananda Sagar College of Department of Computer Science
Engineering Bangalore, India Dayananda Sagar College of Engineering
Bangalore, India
Anupama Vijayakumar*
Assistant Professor
Department of Computer Science
Dayananda Sagar College of Engineering
Abstract - The modern era of technology has a tremendous
impact on the society. With the creation of the ultimate virtual
general template for the same.
assistants, chatbots have become a popular entity in the
conversational services. Chatbots are software programs that II. TYPES OF CHATBOTS
use natural language understanding and processing. Chatbots Before the advent of this modern era of technology, manual
are not just restricted to help the user to complete his tasks such labor played a major role in all sectors of the industry. With
as booking a movie ticket or finding the nearest restaurant, but
this modern evolution, creation of chatbots has successfully
they also provide a source of entertainment, play a major role in
home automation projects, give business strategy tips and help helped in sectors like customer service. However, not all
in other ways. In this paper, we will provide an insight into what chatbots fall under one category. Chatbots are classified
a chatbot is and the types of chatbots. We also propose a based on the ease of user interface, algorithms and the
classification based on the current market trends, ease of underlying technologies used. In this paper, (figure 1) it has
usability and requirements. been proposed that chatbots are mainly categorized into three
types.
Keywords: Chatbot, conversational agent, Artificial Intelligence,
Machine Learning, Natural Language Processing, Natural Menu/Button-Based Chatbots
Processing Understanding, ALICE The most commonly used and the simplest type of chatbots
in the market today are the menu based chatbots, which are in
I. INTRODUCTION form of buttons and top-down menus. These chatbots follow
Technology plays a massive role in the industry and daily the principles of decision trees, where you make your
chores. It serves a variety of purposes and is applied in a decisions to get the ultimate answers. The user is
different way in different parts of the world. Recently, the instructed to make these decisions by selecting their options
public has been fantasized by Artificial Intelligence. and dig deeper to- wards the appropriate response from the
Artificial Intelligence simulates the cognitive abilities of a AI. However, these menu-based chatbots are comparatively
human. To be more precise and closely related to humans, slower in terms of performance and cannot be completely
the AI Chatbots are now replacing human responses with reliable to get the desired answer.
this software. A Chatbot is a computerized program that acts
like a colloquist between the human and the bot, a virtual Keyword Recognition-Based Chatbots
assistant that has become exceptionally popular in recent These chatbots recognizes specific keywords in order to
years mainly due to dramatic improvements in the areas like produce a desired result. They listen to what the users enter
artificial intelligence , machine learning and other underlying and respond accordingly. With the help of the AI technology
technologies such as neural networks and natural language and customized keywords list, the bot determines an
processing. These chatbots effectively communicate with appropriate response to the user by using the algorithms.
any human being using interactive queries. Recently, there’s These chatbots will start to fail when there are keyword
been a massive increase in many cloud-based chatting bot redundancies between several related questions. For
services which have been made available for the example, if a user asked the question ‘How do I set up an
development and improvement of the chatbot sector[1] such auto-login authentication on my phone?’, the bot would
as IBM Watson, Cleverbot, ELIZA chatbot and many others. likely use the keywords like ‘auto’, ‘login’, to determine
These conversational agents have become more responsive which answer is the best to respond with.
and the art of conversation between humans and robots over
the past few years have improved drastically. In this paper, Contextual Chatbots
we have generalized the AI chatbots and described the Contextual chatbots are one of the most technologically
1
advanced bots in the market today. They utilize Machine
Learning and Artificial Intelligence technologies like voice
recognition, speech-to-text conversion algorithms, etc to
interpret the user’s sentiments. The underlying ideology of
this type of bot is to figure out what the user’s intentions are
and correspondingly present a thoughtful answer by
deciphering the pattern in the database. The bot learns and
grows over time by encountering many more experiences. A
simple example of such a bot can be seen in a food delivery
application. Here the previous order history along with the Fig. 1. Proposed Classification of Chatbots
user’s payment options and delivery address are stored on
the database. These chatbots analyze the user’s perspective
and suggest recommendations based on consecutive orders
and user’s likings.
III. TEMPLATE OF THE BASIC TAGS
AIML (Artificial Intelligence Markup Language) is an
advanced markup language which is used to create unique
chatbots like ALICE, derived from Extensible Markup
Language (XML). AIML based chatbot are popular
because they are lightweight and easy to configure[2] making
it easier to build more artificial intelligent programs. They
parse natural language and train the bot using a structured
template. There are various different APIs and package with
AIML files make this system more flexible and interactive Fig. 2. Preference of Chatbots
to use in various fields [2].
IV. APPLICATIONS OF CHATBOTS
<?XML version=”1.0" encoding=”UTF-8”?> Chatbots are more versatile than given credit for. With the
<aiml version=”1.0.1”> rise of advanced Artificial Intelligence, chatbots have
<category> become popular in the past few years as businesses discover
<pattern>...............</pattern> innovative ways to put them to use. Being a beneficial
<template>..............</template> agent, chatbots have made life easier for customers as they
</category> are available 24/7. They have helped businesses in
</aiml> managing tasks in a customized strategic way. Customer
service is one of the major domain where chatbots found a
Few other tags that can be used along with the start but their functionality extends much beyond that.
template tags are given below: (Refer Table II) Chatbots are communication facilitators which can be
integrated into sales & marketing for lead generation,
AIML is a simple pattern language characterized by general collecting visitor information & constantly engaging
inquiries which utilizes AIML tags and formats to interact. customers through the lead funnel. Below are some of the
The entire process takes place in three parts[3]: different kinds of chatbots that are out in the market
• The user enters his/her query on the chatbot interface currently:
• The user’s query is processed to match with
the predefined format template Humorist Chatbot System:
• Pattern matching is done between the knowledge The main ideology behind the Humorist bot is to make the
base that stores the predefined template and the user’s user laugh. Humorist chatbot is a conver- sational agent that
query in order to arrive at a solution provides a sense of humor by telling humorous anecdotes
Finally, this pattern-oriented answer is presented to the which are stored in its knowledge base. It is also capable of
user. listening to jokes to interpret the humorous level of a user. It
has a set of standard Alice categories that allow holding a
general conversation with a user [2]. The chatbot identifies
humorous jokes by identifying certain keywords and
responds accordingly with funny graphical images and
textual responses.
2
a central module present that collectively receives all the data
Dorothy Network Management chatbot: generated by ALICE which is then processed in order to
Every industry and software application requires network produce unique results. Another module that holds the entire
management. Security measures and protocols play an information is the network history information module [4]
important role in network management to prevent which consists of different modules like collect module and
unauthorized access. Dorothy Network Management chatbot history information base which collects the necessary data
is one such bot that takes care of your network via and store it in the information base respectively[4]. All the
management protocols. Based on ALICE technology, there is
TABLE I
REQUIRED BASIC TAGS
BASIC TAGS DESCRIPTION
<aiml> A root tag that indicates the starting and ending of an AIML document.
<category> Forms the basic unit of knowledge and consists of patterns and templates.
<pattern> It is a string intended to correspond to one or more user input and a pattern in matched within this tag.
<template> Specifies the response to an adjusted pattern
TABLE II
ADDITIONAL ADD ON TAGS
<star> Used when embedded in a <srai> tag, this matches wildcard * character(s) in the <pattern> tag
<srai> Used to match the other categories. When a specific keyword is entered, a simple response is returned.
<li> Used within the <random> tag for random responses from the given list. Specifies a list item.
<topic> Used as a buffer to store a context so that responses can be based on that context. Usually
used in Binary type conversation and helps AIML to search categories written within the
context of the topic.
<random> Used to get random potential set of responses. Enables AIML to respond differently to the
same input.
<get> Sets whatever is within the tags to the variable VALUE. It can be retrieved through the
use of a<get> tag.
<set> Output whatever is in the variable VALUE. If VALUE has not been <set>, defaults to “ ”.
<think> Performs whatever is between the tags but not output anything to the user.
<condition> Used to respond to the matching input
<that> Used to respond based on the context.
over time and mimic real conversations with the users. They
information generated by all modules is processed by the usually accept commands in written or oral form enabling
central module and returns to the user through ALICE [4]. them to understand natural language. It controls
communication structure with web service and consists of
Adaptive Modular Architecture based chatbot: three components: client, server, content acquisition. All
Another chatbot that is based on ALICE technology is messages are formatted in an XML and encapsulated in
Adaptive Modular Architecture based chatbot. This SOAP text based message pack. The client contains a voice
conversational agent is based on modular knowledge recognition processing module[2].
representation and proof-of-concept[2]. Knowledge
representation plays an integral part of Artificial Intelligence. V. CONCLUSION
This modular ontology will help the chatbot response in a A chatbot is an ecosystem, a virtual human being that has
more flexible manner. The knowledge representation model been integrated with various industrial applications. With the
is composed of various components: dialogue engine, passage of time, new features are added to the existing
dialogue analyzer, corpus callosum[2]. Corpus callosum plays platform[1] to create better virtual assistants. Chatbots like
an important role as it triggers the model and activates only a Alice and Eliza have created an impact in the world of
particular section of the knowledge base at a given period. technology. Lately, with the concepts of Artificial
Intelligence, Machine Learning, Natural Processing
Web-based voice chatbot: Langauge and recent advancements in machine learning
Just like how Alexa is for Amazon, Siri is for apple and techniques like Deep Learning, it has been made possible to
cortana is for Microsoft, the web-based voice chatbots have develop humanoid chatbots. Samsung Technology and
come to light. This Web-based system uses voice Advanced Research Labs (STAR) have developed a
recognition technologies to interact with its users. Based on technology, Neon, a chatbot that has been designed to behave
ALICE bot engine, these intelligent digital assistants learn like a human with emotional ability and intelligence. These
3
bots aren’t “know-it-all” bots instead programmed to act like
a real one. Chatbots, unlike other AI tools, will be used to
enhance human capabilities and free humans to be more
innovative and act upon strategic tactics.
VI.REFERENCES
[1] A M Rahman, Abdullah Al Mamun, Alma Islam. "Programming
challenges of chatbot: Current and future prospective", 2017 IEEE
Region 10 Humanitarian Technology Conference (R10-HTC), 2017
[2] Md. Shahriare Satu, Md. Hasnat Parvez, Shamim-Al-Mamun.
"Review of integrated applications with AIML based chatbot", 2015
International Conference on Computer and Information Engineering
(ICCIE), 2015
[3] Bhavika R. Ranoliya, Nidhi Raghuwanshi, Sanjay Singh. "Chatbot for
university related FAQs", 2017 International Conference on
Advances in Computing, Communications and Informatics
(ICACCI), 2017
[4] Michelle Denise Leonhardt, Liane Tarouco, Rosa Maria Vicari, Elder
Rizzon Santos, Michele dos Santos da Silva. "Using Chatbots for
Network Management Training through Problem-based Oriented
Education", Seventh IEEE International Conference on Advanced
Learning Technologies (ICALT 2007), 2007
