Limericking part 1: context and haikus.

One of the most exciting fields within machine learning and data science is natural language processing. Having a machine be able to parse and generate plausibly human sounding language is both of enormous practical value and also notoriously difficult. Human language is messy, filled with the sort of irregularities that computers can't handle. Even relatively simple tasks like tagging what part of speech a given word is can be hard and context dependent (is'permit' a noun or a verb?). Even the most powerful and successful implementations of NLP can feel a little off.