International Research Journal of Engineering and Technology (IRJET) e-ISSN: 2395-0056
Volume: 06 Issue: 11 | Nov 2019 www.irjet.net p-ISSN: 2395-0072
© 2019, IRJET | Impact Factor value: 7.34 | ISO 9001:2008 Certified Journal | Page 1814
Review of Chatbot System in Marathi Language
Darshan Navalakha
1
, Manjiri Pittule
2
, Ravina Mane
3
, Amit Rathod
4
, Prof. N.G. Kharate
5
1,2,3,4
Students, Comp Dept., VIIT College, Pune, India
5
Guide, Comp Dept., VIIT College, Pune, India
---------------------------------------------------------------------***----------------------------------------------------------------------
Abstract - In the modern Era of technology, Chatbots is the next big thing in the era of interactive services. Chatbots is a virtual
person who can effectively talk to any human being using collaborative textual skills. A virtual person is based on machine
learning and Artificial Intelligence (AI) concepts and due to dynamic nature, there is a drawback in the design and development of
these chatbots as they have built-in AI, NLP, programming and conversion services. Chatbot acts like routing agent that can
categorize user context in conversation. Chatbot helped with natural language processing (NLP) to analyze the request and extract
some keyword information. In this system chatbot is designed according to query-based system in Marathi language (Indian
Language). User asks the question to system; the system automatically replay all answer through chatbot. OCR concept is used to
fetch data from pdf or images in the text format. All the query related information is added in this system. Although the significant
work is not carried out for Marathi language chatbot but many researchers and organization have started building chatbot system
in this field.
Key Words: NLP, OCR, Data-set, Pattern Matching, Machine Translation.
1. INTRODUCTION
A chatbot is a program intended to counterfeit a smart communication on a text or spoken ground. But this paper is based on
the text only chatbot. Chatbot categorize the user input as well as by using pattern matching, access information to provide a
predefined
Acknowledgement, based on the sentence given by the user. When the input is bringing into being in the database, a response
from a predefined pattern is given to the user. A Chatbot is executed using pattern comparing, in which the order of the
sentence is recognized and a saved response pattern is adapt to the select variables of the sentence. Chatbots are mainly
developed is conversational dialogue engine which is built in Python, which makes it possible to reply based on the collections
of all the known conversations. This chatbot system uses Marathi language. All the query related data is available in this
system’s database.
Text Recognition usually abbreviated to OCR, involves a computer system intended to interpret images of typewritten text
(usually captured by a scanner) into machine editable text or to interpret pictures of characters into a standard encoding
scheme representing them. OCR commenced as a field of research in artificial intelligence and computational vision. Text
Recognition used in official task in which the large data have to type like post offices, banks, colleges etc., in real life
applications where we want to collect some information from text written image. People wish to scan in a document and have
the text of that document available in a .txt or .docx format.
2. LITERATURE SURVEY
The making and execution of chatbots is still a developing area, heavily related to artificial intelligence and machine learning, so
the provided solutions, while possessing obvious advantages, have some important limitations in terms of functionalities and
use cases. However, this is changing over time.
Mr. A.M.Rahman has identified some programming challenges of chatbot, For bot to work resourcefully it needs to provide vast
logical resources which are I/P, O/P and entity phrases. It should be given care on singular, plural forms, Synonyms, Antonyms
and the most important is the sentimental analysis [1].
Response generation using Intent Classification and Entity Recognition. Response selector selects response which should work
better for the user. Bot is based on the integration, in which information “bot sends” commands into web service and gets it
results [1].
Belfin R.V, Shobhana A.J, Megha Manilal, Ashly ann Mathew, Blessy Babu they have proposed A Graph Based Chatbot for cancer
Patients. It is presented in text and Audio. The Continuous Communication with Bot bring positive attitude in patients. In their
research work they have implemented, Knowledge Based Chatbot which fetch appropriate data from Cancer database and scrap
data from different Cancer forums using Beautiful Soap. Some data pre-processing techniques like tokenization, punctuation
removal, stop word removal, stemming is performed.[2]