This notebook uses the Pomegranate library to build a Hidden Markov Model for part of speech tagging with a universal tagset.
This is a project from Udacity's NLP Nanodegree where I built and trained the model to predict parts of speech labels for each word in the input sentence. I contributed the key architectural components for the model (marked under #TODO lines), while Udacity provided the remaining code.
NOTE: If you are prompted to select a kernel when you launch a notebook, choose the Python 3kernel.