Information Retrieval | Part 2 - Term Document Matrix

In this series, we're going to explore the concept of Information Retrieval. We'll use information retrieval research as our guide, and build a text search engine of our own using C# .NET. We'll also use Python with Jupyter notebook to explore high-level ideas quickly.

In this video, we'll look at a preliminary indexing structure called a Term-Document matrix, do some back-of-the-envelope calculations on the size of our example corpus and the corresponding index, and consider the strengths and drawbacks of using this type of data structure to support the Boolean Retrieval model for search.

Here's a link to the IR book at Stanford NLP: https://nlp.stanford.edu/IR-book/

Link to the repo: https://github.com/wesdoyle/Javelin.NET