Automatic Question Generation Using SpaCy

Sujgure, Priyanka Ashok (2022) Automatic Question Generation Using SpaCy. Masters thesis, Dublin, National College of Ireland.

Preview	PDF (Master of Science) Download (1MB) | Preview
Preview	PDF (Configuration manual) Download (1MB) | Preview

Abstract

The availability of learning resources on online learning platforms throughout the world has increased significantly, with some open-source Massive Open Online Courses (MOOCs), ed-tech businesses, and schools migrating to an online learning-based approach. This environment provides a wealth of possibilities and enables constant access to information, but it hinders the capacity to grasp crucial concepts. Improving the quality of understanding is a major issue that requires long-term solution. One method to enhance the teaching/learning experience it is to ask questions. It stimulates critical thinking and effective learning; however, writing questionnaires for every piece of online information is time-consuming and requires an automated solution. The proposal seeks to address the issues by automating question formation just with textual inputs. It uses SpaCy library of the Natural Language Processing (NLP) to do so. The NLP pipeline of tokenization, Parts of Speech (POS) tagging, etc. has been implemented to form Fill in the Blanks (FIB) and True or False types of questions. The use of pre-trained models such as BERT is been done here. Experiment is performed out on two different datasets to evaluate the results. The experiment performed shows more than 50% good quality questions generated in both the question types .

Item Type:	Thesis (Masters)
Subjects:	Q Science > QA Mathematics > Electronic computers. Computer science T Technology > T Technology (General) > Information Technology > Electronic computers. Computer science P Language and Literature > P Philology. Linguistics > Computational linguistics. Natural language processing L Education > LC Special aspects / Types of education > Distance Learning
Divisions:	School of Computing > Master of Science in Data Analytics
Depositing User:	Tamara Malone
Date Deposited:	13 Mar 2023 13:54
Last Modified:	13 Mar 2023 13:54
URI:	https://norma.ncirl.ie/id/eprint/6320

Actions (login required)

View Item