Date of Submission

Spring 5-18-2020

Degree Type

Thesis

Degree Name

Master of Science in Computer Science (MSCS)

Department

Computer Science

Committee Chair/First Advisor

Dan Lo

Track

Big Data

Chair

Coskun Cetinkaya

Committee Member

Junggab Son

Committee Member

Selena He

Abstract

A text is a set of words conveying a particular semantic based on their order, representation and structure. Those elements can be associated through a different set of interpretations, based on frequency and proportionality. The problem with context is that numbers do not help understand the semantics and fall short to convey the message of the text. The graphical representation of text semantics focuses on the conversion of text to images. Contrarily to word clouds that simply produce frequency mapping of words within the text and topic models that essentially give context to word frequencies and proportionalities, images keep intact the semantic and the context of the words in the text. They provide a deeper understanding and can be better interpreted. Models such as AttnGAN already exist to convert text into images with a certain level of success, but there has not been work done concerning the conversion of long and complex texts in an image or a set of images. The goal of this analysis is to first, provide an understanding of how we divide the text in bits that improve the resulting image and how does the summarization methodology affect the image result.

Share

COinS