International Research Journal of Engineering and Technology (IRJET) e-ISSN: 2395-0056
Volume: 09 Issue: 04 | Apr 2022 www.irjet.net p-ISSN: 2395-0072
© 2022, IRJET | Impact Factor value: 7.529 | ISO 9001:2008 Certified Journal | Page 3207
Vikalp - Automatic multiple choice questions generator
Amit Singh
1
, Parth Kalbag
2
, Divya Kukreja
3
, Ritu Kalyani
4
1
Assistant Professor, amit.singh@ves.ac.in, Dept. of AI and Data, Vivekanand Education Society’s institute
of Technology, Mumbai, Maharashtra, India
2-4
Student, 2018.parth.kalbag@ves.ac.in, 2018.divya.kukreja@ves.ac.in, 2018.ritu.kalyani@ves.ac.in, Dept. of
Information Technology, Vivekanand Education Society’s institute of Technology, Mumbai,
Maharashtra, India
---------------------------------------------------------------------***---------------------------------------------------------------------
Abstract - In any education system, examinations are
conducted to judge the caliber of the students. To conduct the
examination, teachers need to generate the questions
manually which is a very time-consuming process. To reduce
time and effort, a system through which multiple choice
questions can be automatically generated for user-given text is
proposed in this paper. Fill In the Blanks, True or False and
Match the Following are the types of multiple-choice questions
covered.
Key Words: Automatic Multiple choice questions,
Natural Language Processing, Mcq’s, Distractors,
Conceptnet, Wordnet, Sense2Vec.
1. INTRODUCTION
In this modern world where technology is always evolving
and has increased its reach to various sectors of the
educational industry, various schools and colleges have
adopted the e-learning platforms in which they assess
students through various exams like GATE, CAT, College
Exams, etc. it has be-come quite a cumbersome task to
generate multiple-choice questions for the whole syllabus.
MCQ-style questions are a basic instructional tool that may
be used for several reasons. These types of questions can
affect student learning in addition to serving as an
assessment tool. In certain examinations, the only way of
ensuring proper assessment of students is by generating
good quality MCQs so that they can explore much more than
usual and are well-suited to the current e-learning measures.
The paper focuses on generating various types of MCQs like
Fill in the Blanks, True or False, and Match the following.
Multiple Choice questions are a form of evaluation in which
respondents are inquired to choose the most appropriate
reply out of the choices from a list. The MCQs are formed
from basically two entities: a question and various possible
options including the correct answer. The question is formed
by determining which type of question can be formed. For
e.g., “The number of days in a week are ” For the following
sentence as the sentence contains a numerical value so the
type of question generated can be a numerical one with the
correct answer replaced by a “ ” and suppose considering
another example “Still, numbers for server use of Windows
(that are comparable to competitors) show one third market
share, similar to that for end user use.”. If this is the
respective question generated, then the type of MCQ the
system should generate is either a True or False or a Fill in
the blank type of MCQ.
The major challenge in generating any MCQ is the
requirement for great distractors, i.e., distractors ought to
show up as a conceivable reply to the question indeed to an
understudy with great information on the space. At the same
time, it should not be a substitute reply or synonym. Besides,
a well written MCQ should contain sufficient data to answer
the question. For example: “The color of the blood is .” and
the corresponding distractors are: Red, Maroon, Dark Red,
Crimson Red. As in this example all the distractors have very
similar meaning. Hence, the distractors should actually make
more sense as in this example: “The color of the blood is .”
and the corresponding distractors are: Red, Blue, Green,
White. Here, all the distractors have similar context but are
clearly distinguishable from each other and are making a
good impact.
2. LITERATURE SURVEY
This section discusses research works which proposed the
idea for Automatic MCQ generation. Cloze Questions contain
questions where questions contain one or more blanks and
multiple choices listed to pick an answer is discussed in [1]. It
was actually a goal-oriented system, that is, a specific field
based on cricket world cup data. Cloze system is divided into
three modules: sentence selection, keyword selection and
distractor selection. So, the end output gives an English
article on cricket World cup and the system generates Cloze
questions.
Real time multiple-choice question generation for language
testing and English grammar is discussed in [2]. For the
application, NLP technique and basic machine learning semi
supervised algorithm such as Naive Bayes Classifier and
KNearest Neighbors algorithm were used. A real-time system
generates only one type i.e Fill in the Blanks type of questions
on English grammar and vocabulary from online news
articles which takes an HTML file as input and turns it into
the quiz session.