Understanding and Creating Word Embeddings
Word embeddings allow you to analyze the usage of different terms in a corpus of texts by capturing information about their contextual usage. This lesson is designed to get you started with word embedding models. Through a primarily theoretical lens, this lesson will teach you how to prepare a corpus and train a word embedding model. You will explore how word vectors work, how to interpret them, and how to answer humanities research questions using them.
This lesson involves running some Python code: a basic familiarity with Python would be helpful, but no particular technical expertise is required.
Reviewed by:
- Anne Heyer
- Ruben Ros
Learning outcomes
After completing this lesson, you will be able to:
- Know what word embedding models and word vectors are, and what kinds of questions we can answer with them
- Create and interrogate word vectors using Python
- Put together the corpus you want to analyze using word vectors
- Understand the limitations of word vectors as a methodology for answering common questions