Named entity recognition

Now, we arrive at another important concept called the named entity recognition, which aims to sort textual content into default categories such as the names of persons, organizations, locations, expressions of time, quantities, monetary values, and so on. The process is also known as entity identification, entity chunking, or entity extraction. This is a very powerful technique to understand large chunks of textual content in an automated manner.

Here, we will use an open source module to demonstrate the concept called Stanford NER (named entity recognizer), which is a widely used and one of the most popular named entity recognition tools. As Stanford NER is implemented in Java, we'll use the NLTK library, which provides an interface of Stanford NER to be used using Python.

The download is a zipped file (mainly consisting of classifiers). After unpacking, we have all needed files for running under Windows or Unix/Linux/macOS, a simple GUI, and the ability to run as...