Named Entity Recognition is one of the most common NLP problems. The goal is classify named entities in text into pre-defined categories such as the names of persons, organizations, locations, expressions of times, quantities, monetary values, percentages, etc. What can you use it for? Here are a few ideas - social media, chatbot, customer support tickets, survey responses, and data mining!

Click this button to open a Workspace on FloydHub that will train this model.

In this notebook we will perform a Sequence Tagging with a LSTM-CRF model to extract the named entities from the annotated corpus.

Entity tags are encoded using a BIO annotation scheme, where each entity label is prefixed with either B or I letter. B- denotes the beginning and I- inside of an entity. The prefixes are used to detect multiword entities, e.g. sentence:"World War II", tags:(B-eve, I-eve, I-eve). All other words, which don’t refer to entities of interest, are labeled with the O tag.

We will:

• Preprocess text data for NLP
• Build and train a Bi-directional LSTM-CRF model using Keras and Tensorflow
• Evaluate our model on the test set
• Run the model on your own sentences!