Source: Georgia Tech Digital Humanities Lab
URL: Data Processing with nltk
The Python package, nltk, is a great starter kit for anyone wanting to learn natural language processing. It can easily perform functions in any text such as finding parts of speech, tagging entities of any kind (person, place, company, etc.), figure out the stem of a word, and so much more. In this project, I’ll focus on finding and tagging people, places, and/or corporations, also known as Named Entity Recognition (NER). NER problems can be broken down into two parts: detecting entities and classifying them into the kind of entity that they are (person, place, title, etc.). Another helpful way…
Read More: Data Processing with nltk
Georgia Digital Humanities Consortium