How Machines Understand Text: Foundations of Natural Language Processing

From spam filters and search engines to voice assistants and recommendation systems, natural language processing (NLP) powers many of the technologies we use every day. But how do computers actually understand human language? Join ASU Library's Unit for Data Science and Analytics for the first session of this foundational mini-series as we explore how machines process, analyze and learn from text data.

In this session, we will explore how computers transform human language into something they can process and analyze. We will introduce the concept of tokens, discuss how machines identify patterns and relationships in text, and examine how language can be transformed into numerical representations that computers can work with. Using real-world examples, we will explore techniques such as sentiment analysis, text classification, and topic modeling to better understand how NLP is used to organize information, analyze opinions, and uncover themes hidden within large collections of text.

Join us as we explore the fundamentals of Natural Language Processing (NLP) and demonstrate how to apply these techniques through beginner-friendly examples using Python. Many of the concepts we will introduce in this lab, such as tokens, language patterns, and numerical representations of text, also form the foundation of modern generative AI systems, which we will discuss in the second session of this mini-series. This foundational series is designed for a beginner-to-intermediate audience. If you have never worked with NLP before, this session is for you. No matter where you are in your data journey, join us to learn how machines understand language and text.