11 Taming text with graphs
This chapter covers
- A simple approach to decompose a text and store it in a graph
- How to extract the hidden structure of unstructured data via natural language processing
- An advanced graph model for taming text
Text, text, and more text! We are surrounded by textual data. Much of the world’s knowledge is stored and shared using text in natural language. This has been true since the beginning of human history, when we started sharing knowledge in different languages—first just by voice and later, to make it permanent, by writing.
Natural language is the way in which we interact with other humans. We begin learning it as infants—yet understanding language is one of the most complex tasks a machine can do. Nevertheless, computer scientists, data scientists, and machine learning practitioners have worked hard to make machines capable of dealing with textual data, providing for complex solutions that leverage text to offer advanced features to the final users. Let’s consider the most common solutions that you likely use every day, probably without even noticing just how complex and useful they are.