Naive Bayes versus BERT: Jupyter notebook assignments for an introductory NLP course

Jennifer Foster, Joachim Wagner


Abstract
We describe two Jupyter notebooks that form the basis of two assignments in an introductory Natural Language Processing (NLP) module taught to final year undergraduate students at Dublin City University. The notebooks show the students how to train a bag-of-words polarity classifier using multinomial Naive Bayes, and how to fine-tune a polarity classifier using BERT. The students take the code as a starting point for their own experiments.
Anthology ID:
2021.teachingnlp-1.20
Volume:
Proceedings of the Fifth Workshop on Teaching NLP
Month:
June
Year:
2021
Address:
Online
Editors:
David Jurgens, Varada Kolhatkar, Lucy Li, Margot Mieskes, Ted Pedersen
Venue:
TeachingNLP
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
112–114
Language:
URL:
https://aclanthology.org/2021.teachingnlp-1.20
DOI:
10.18653/v1/2021.teachingnlp-1.20
Bibkey:
Cite (ACL):
Jennifer Foster and Joachim Wagner. 2021. Naive Bayes versus BERT: Jupyter notebook assignments for an introductory NLP course. In Proceedings of the Fifth Workshop on Teaching NLP, pages 112–114, Online. Association for Computational Linguistics.
Cite (Informal):
Naive Bayes versus BERT: Jupyter notebook assignments for an introductory NLP course (Foster & Wagner, TeachingNLP 2021)
Copy Citation:
PDF:
https://aclanthology.org/2021.teachingnlp-1.20.pdf