I know I've been a little quiet for a bit. Here are a few things I've been up to:
- Scaling Stanford CoreNLP in the cloud to handle millions of long-form documents a day
- Building out libraries for manipulating and accessing this data
- Performing machine learning against features extracting from these parses
We're working on writing a draft for Taming Text, 2nd. Edition, edited by Grant Ingersoll, Thomas Morton and Drew Farris. So that's really exciting!