It was fun creating the NanoGenMo story. It gives insight into how English grammar can be broken down and made nonsensical. I used the corpus Academy Award data from the Wiki Corpus, since I thought it would be fun to reverse the “Academy Award” process by starting from the beginning, a casting call. So, I generated some excerpts of casting calls from the Academy Award casting data. I used Allison’s Python notebook “Corpus-driven-narrative-generation” to generate the stories from a corpus and Tracery grammars.
Link to notebook (need to have the original awardWork.tsv file to run)
Here are the rules:
Here are some of favorite excerpts:
ABBY LEE - ITP BLOG 