Physical Sciences and Mathematics Commons^™

Dictionary-Based Data Generation For Fine-Tuning Bert For Adverbial Paraphrasing Tasks, Mark Anthony Carthon

Theses and Dissertations

Recent advances in natural language processing technology have led to the emergence of

large and deep pre-trained neural networks. The use and focus of these networks are on transfer

learning. More specifically, retraining or fine-tuning such pre-trained networks to achieve state

of the art performance in a variety of challenging natural language processing/understanding

(NLP/NLU) tasks. In this thesis, we focus on identifying paraphrases at the sentence level using

the network Bidirectional Encoder Representations from Transformers (BERT). It is well

understood that in deep learning the volume and quality of training data is a determining factor

of performance. The objective of …

The Use Of Digital Applications And Websites In Completing Math Assignments, Ronna Williams

CUP Ed.D. Dissertations

There is a large assortment of digital applications and websites available for students to use in completing their math assignments. The problem is how and why they are using these applications. This study looked at the different applications and websites used by students, including Slader, Wolfram Alpha, Symbolab, Desmos, and Photomath. The study then explored why students used these applications and websites. The idea of plagiarism in mathematics was presented to the students in this study. The review of the literature included the concepts of plagiarism and cheating and illustrated that students have a history of using tools for accomplishing …