Login (DCU Staff Only)
Login (DCU Staff Only)

DORAS | DCU Research Repository

Explore open access research and scholarly works from DCU

Advanced Search

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

Foster, Jennifer orcid logoORCID: 0000-0002-7789-4853 and Wagner, Joachim orcid logoORCID: 0000-0002-8290-3849 (2021) Naive Bayes versus BERT: Jupyter notebook assignments for an introductory NLP course. In: Fifth Workshop on Teaching NLP, 10-11 June 2021, Online.

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.
Metadata
Item Type:Conference or Workshop Item (Paper)
Event Type:Workshop
Refereed:Yes
Subjects:Computer Science > Computational linguistics
DCU Faculties and Centres:DCU Faculties and Schools > Faculty of Engineering and Computing > School of Computing
Research Initiatives and Centres > ADAPT
Published in: Proceedings of the Fifth Workshop on Teaching NLP. . Association for Computational Linguistics (ACL).
Publisher:Association for Computational Linguistics (ACL)
Official URL:https://doi.org/10.18653/v1/2021.teachingnlp-1.20
Copyright Information:© 2021 The Association for Computational Linguistics
Funders:Science Foundation Ireland (SFI) Frontiers for the Future programme (19/FFP/6942).
ID Code:28290
Deposited On:27 Apr 2023 15:03 by Joachim Wagner . Last Modified 27 Apr 2023 15:03
Documents

Full text available as:

[thumbnail of 2021.teachingnlp-1.20.pdf]
Preview
PDF - Requires a PDF viewer such as GSview, Xpdf or Adobe Acrobat Reader
Creative Commons: Attribution 4.0
118kB
Downloads

Downloads

Downloads per month over past year

Archive Staff Only: edit this record