ORCID Identifier(s)

0000-0002-3958-4571

Graduation Semester and Year

2020

Language

English

Document Type

Thesis

Degree Name

Master of Science in Computer Engineering

Department

Computer Science and Engineering

First Advisor

Elizabeth Diaz

Abstract

Research papers and journals have always played a crucial role in the field of research and development. However, these research papers usually have a complex usage of language which limits the range of target readers. The language and the terms used in these literary works can make the concept or the topic tough to understand for a naive reader. The goal of this project is to simplify a complex piece of literature into something meaningful without sounding verbose. The idea is based upon Nobel Prize-winning physicist Richard Feynman’s learning technique known as the Feynman Technique that emphasizes the usage of words that are simple to understand. Such simplification can help a researcher gain more information from more literature in less amount of time. The proposed system can also be used to simplify other text documents apart from research papers and journals. This novel model based on simplicity can be considered a new learning model.

Keywords

Summarization, Extractive summariztion, Simplification, Text mining

Disciplines

Computer Sciences | Physical Sciences and Mathematics

Comments

Degree granted by The University of Texas at Arlington

Download

Share

COinS