Named Entity Recognition
Table of Contents
Named Entity Recognition (NER)
We'll start with the question - "What is Named Entity Recognition (NER)?". NER is a subtask of information extraction that locates and classifies named entities in a text. The named entities could be organizations, persons, locations, times, etc.
We'll train a named entity recognition system that could be trained in a few seconds (on a GPU) and will get around 75% accuracy. Then we'll load in the exact version of the model, which was trained for a longer period of time. We can then evaluate the trained version of the model to get 96% accuracy! Finally, we'll test the named entity recognition system with new sentences.
The Posts In Order
These are the posts where we'll actually implement the code.