A Practical Introduction to Natural Language Processing

Abstract

This lecture will focus on the practical aspects of manipulating natural language for computation. It will include methods for representing natural language in computers (features, embeddings), applying classic approaches to preprocessing text (stemming, lemmatization), and incorporating context into these representations (n-grams, transformers). The lecture follows practical examples using synthetic and real text. The format is intended to be interactive; some experience running a Google Colab notebook is recommended.