Striking a Balance between Classical and Deep Learning Approaches in Natural Language Processing Pedagogy

TL;DR

This paper advocates for integrating classical NLP algorithms with deep learning approaches in teaching to enhance student understanding and provide a balanced educational perspective.

Contribution

It presents a practical framework for balancing classical and deep learning methods in NLP pedagogy based on course experiences in Australia and India.

Findings

Classical approaches help build intuitive understanding of NLP.

Including classical methods enriches NLP education.

Balance improves student comprehension of complex models.

Abstract

While deep learning approaches represent the state-of-the-art of natural language processing (NLP) today, classical algorithms and approaches still find a place in NLP textbooks and courses of recent years. This paper discusses the perspectives of conveners of two introductory NLP courses taught in Australia and India, and examines how classical and deep learning approaches can be balanced within the lecture plan and assessments of the courses. We also draw parallels with the objects-first and objects-later debate in CS1 education. We observe that teaching classical approaches adds value to student learning by building an intuitive understanding of NLP problems, potential solutions, and even deep learning models themselves. Despite classical approaches not being state-of-the-art, the paper makes a case for their inclusion in NLP courses today.