Final Presentation

CHATBOT
Project Id-
by
Bhavika Aggarwal (2001280100023)
Isha chaudhary (2001280100036)
Vanshika panwar (2001280100081)
Sakshi Chaudhary (2001280100065)
Under the Supervision of
Mr. Sanjeev Giri, Mr. Ankur Gupta
DEPARTMENT OF COMPUTER SCIENCE AND

ENGINEERING BHARAT INSTITUTE OF
TECHNOLOGY , MEERUT
Affiliated to
DR. APJ ABDUL KALAM TECHNICAL UNIVERSITY
(Formerly Uttar Pradesh Technical University, Lucknow)
CONTENTS
1. INTRODUCTION
2. LITERATURE
SURVEY
3. PROPOSED WORK
4. DESIGN
5. RESULT
6. CONCLUSION
7. REFERENCES
INTRODUCTION
⚫ “Can machines think?” This is the question asked by Alan Turing which has since
spawned numerous, Passionate debates on the subject of artificial intelligence It
has also spawned the famous Turing Test, a test Which determines if a particular
machine (or algorithm?) can pass as a human. Since its inception, the Turing Test
has, in fact, been passed by a few artificial intelligence algorithms. Some of these
algorithms represent the latest technology in terms of artificial intelligence.
⚫ Artificial intelligence (AI) is part of a broad field called cognitive science, which is
simply a study of the mind and the way it works. For the purposes of cognitive
science, artificial intelligence is defined as “a codification of knowledge will
finally explain intelligence”. However, when it comes to software engineering, the
purpose of AI is to use knowledge to solve real-world problems. One of these
problems, similar to the problem of the Turing Test, is how to make an artificial
device or creatures appear more human. To address this problem, a technology has
been created called chatbots. These are AI algorithms that process natural language
and, using the analysis that results from the processing, output an intelligent
response.
⚫ Paper layout is as follows: Section 2 highlights literature survey, Section 3 explains
proposed system in brief, and Section 4 explains the design on Chabot, Section 5
on implementations and Section 6 accounts for some concluding remarks.
LITERATURE
SURVEY
It explains the design of a Chabot that is specifically tailored for providing FAQBot
system for university students and with the objective of an undergraduate advisor in
student information desk. The Chabot accepts natural language input from users,
navigates through the Information Repository and responds with student information in
natural language.
⚫ [1]. Jessel Serrano, Fernando Gonzalez, Janusz Zalewski2015, “ CleverNAO:

The Intelligent Conversational Humanoid Robot “.
⚫ [2]. Comparative studies of AIML by yungang wei, Bo sun, Boying sun and
Xiaoming zhu - 2016
⚫ [3]. Hadeel Al-Zubaide, and Ayman A. Issa, “Ontology based Chabot “.
⚫ [4]. Vincenzo Di Lecce*, Marco Calabrese,DomenicoSoldo and Alessandro

Quarto , “Dialogue-Oriented Interface for Linguistic Human Computer
Interaction”.
PROPOSED
o In the proposed system we are creatingWORK
a Chabot that can reply to the user in the most
effective way. This approach is proposed to model and operate the chat bots.
o It uses appropriate mapping technique to transform ontologies [3] and knowledge into
relational database and then use that knowledge to derive its chats. The data that is
stored in the database is used to map with the queries asked by the user. The user gives
the question as a string and that string is taken as a JSON object and that object is
processed using various NLP algorithms such as porter-stemming, Wordnet, TF-IDF.
These algorithms will provide the keywords and those keywords will be matched to the
keywords in the database to extract the required answer string.
o 3.1 Ontology technique This technique is responsible on processing user input for getting
the needed answer. Several functionalities should be taken into account before start
searching for a match in database and then succession in getting the best answer. Such
functionalities include input tokenization, stopper filtering, stemming and synonyms
handling. Figure 1 illustrates the four functionalities and their sequence.
Design
The chat agent accepts to student’s query and extracts the keywords (nouns and verbs
from the question using a lexical parser. Then the keywords are compared with the
category list database. With the category selected, the keywords are then compared with
the questions under the category. The answer to the question is then obtained using most
commonly occurring keyword. Figure 2 represent user and admin activities. Where user
corresponds to a person who use the bot and admin add the related questions and
corresponding answers to database.
Usually all the answers are store directly in database but question are converted into list
of keywords (words obtained after applying ontology based approach) are stored in
database. Figure 3 gives ER diagram for relational database .whenever user ask any
question that is taken as JSON object then converted in to list of keywords (after applying
ontology based technique) map this with all list of keywords in database and calculate
rank for each questions using TF-IDF finally retrieve the answer of that question which
has maximum rank
RESUL
T
Fig 3. Result of Question answered by Candidate

• A JWNL Properties file is an XML file that can be validated using the included
DTD or XSD.basically the properties file allows to specify three properties:-
Dictionary class: This defines the class used to interface with the dictionary.
JWNL comes with three dictionary classes - MapBackedDictionary,
FileBackedDictionary, and DatabaseBackedDictionary. exactly 1 dictionary tag is
required in a properties file. If there is more than one, the first one will be used.
User: Hello
Bot: Hello there!
CONCLUSION
❖ This approach for the result (answer) of Chabot focuses on the case of a low
computational and data budget. The results have shown that this kind of approach
needs large quantity of data to be trained from scratch. In the scenario of having a
small dataset (question and answer) and a task to perform, language processing can
be used to find – related and appropriate answers that have been trained on large
database and for other purposes. Even though this field is underway of improvising
the process a lot of work of optimization is required. As a future work some other
techniques to obtain an accurate prediction of the answer (result) can be devised
which takes less time for its computation
REFERENCES
 [1]. Jessel Serrano, Fernando Gonzalez, Janusz Zalewski2015, “ CleverNAO: The

Intelligent Conversational Humanoid Robot “.
 [2]. Comparative studies of AIML by yungang wei, Bo sun, Boying sun and
Xiaoming zhu - 2016
 [3]. Hadeel Al-Zubaide, and Ayman A. Issa, “Ontology based Chabot “.
 [4]. Vincenzo Di Lecce*, Marco Calabrese,DomenicoSoldo and Alessandro Quarto ,
“Dialogue-Oriented Interface for Linguistic Human Computer Interaction”.
 [5]. Abran, A., Cuadrado, J., Garc´ ıa-Barriocanal, E., Mendes, O., S´ anchez-Alonso,
S., and Sicilia, M., (2006) , ”Ontologies for Software Engineering and Software
Technology”. Berlin Heidelberg: Springer-Verlag.
 [6]. Wordnet, (2010). Wordnet Project [online]. WN Team. Available from:
http://wordnet.princeton.edu/ [Accessed 05/21/2011].
 [7]. SupratipGhose and JagatJoytiBarua, “Topic specific Dialogue based Natural
Language”.
THANK
YOU
Project Id-
by
Bhavika Aggarwal (2001280100023)
Isha chaudhary (2001280100036)
Vanshika panwar (2001280100081)
Sakshi Chaudhary (2001280100065))
Under the Supervision of

Mr. Sanjeev Giri,
Mr. Ankur Gupta

Final Presentation

Uploaded by

Copyright:

Available Formats

Final Presentation

Uploaded by

Document Information

Original Description:

Original Title

Copyright

Available Formats

Share this document

Share or Embed Document

Sharing Options

Did you find this document useful?

Is this content inappropriate?

Copyright:

Available Formats

Final Presentation

Uploaded by

Copyright:

Available Formats

CHATBOT

DEPARTMENT OF COMPUTER SCIENCE AND

⚫ [1]. Jessel Serrano, Fernando Gonzalez, Janusz Zalewski2015, “ CleverNAO:

⚫ [4]. Vincenzo Di Lecce*, Marco Calabrese,DomenicoSoldo and Alessandro

Fig 3. Result of Question answered by Candidate

 [1]. Jessel Serrano, Fernando Gonzalez, Janusz Zalewski2015, “ CleverNAO: The

Under the Supervision of

You might also like