Intro to Language Models in Python

From spam filters to ChatGPT, computer and AI systems have to work with language models all the time. In this course, you will learn how to build and work with the most common language models in data science, including bag-of-words, tf-idf, and word embeddings. Learn the basic skills you need before working with more advanced AI language models.

Syllabus

Welcome to Language Models with Python: A brief overview of what you will learn in this course.

Informational: Welcome to Language Models with Python

Bag-of-Words Language Model: Whet your language model appetite with the widely used Bag-of-Words. Develop the underlying functionality in Python, then use scikit-learn.

Lesson: Bag-of-Words Language Model
ExternalResource: Working with Text Data | scikit-learn
Project: Mystery Friend
Quiz: Bag-of-words language model

Term Frequency-Inverse Document Frequency: Rethink topic models with term frequency-inverse document frequency (tf-idf), which adjusts the importance of words within a document.

Lesson: Term Frequency–Inverse Document Frequency
ExternalResource: Working with Text Data | scikit-learn | From Occurrences to Frequencies
Project: Read the News Analysis
Quiz: Term Frequency-Inverse Document Frequency