Striking a Balance between Classical and Deep Learning Approaches in Natural Language Processing Pedagogy
This addresses curriculum design challenges for NLP educators, though it is incremental as it builds on existing pedagogical debates.
This paper examines how to balance classical and deep learning approaches in NLP pedagogy by analyzing two introductory courses in Australia and India, arguing that teaching classical methods helps students build intuitive understanding of NLP problems and solutions.
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.