Computational tools and statistical analysis are often deployed as a method to “read” texts. But what about using these same techniques to write them? In this workshop, we’ll investigate the state of the art of natural language processing with an eye toward using the sometimes-unintuitive abstractions of language produced by computational models to make programs that create surprising and poetic creative writing.

Workshop costs: 25,- (includes drinks)
Tickets

Objectives:
In this three-hour workshop led by Allison Parrish the participants will get:
- an understanding of how machine learning processes approach "meaning" in language (i.e., word vectors)
- play with example code for creatively "cutting up" texts based on semantic similarity, based on source texts of the participants' choice

Participants would work with multiple source texts and then "remix" them by swapping out parts based on their word-vector similarity. A good example of the outcomes can be seen at Allison Parrish’s project Plot to Poem http://static.decontextualize.com/plot-to-poem.html

Participants:
For this workshop no experience with code is necessary. Participants need to bring their laptop.
If the workshop attracts more tech-savvy people we’ll “scale up” the technical content of the material.

Workshop participants will develop a number of small projects in text analysis and poetics using a public domain text of their choice. In becoming familiar with contemporary techniques for computational language analysis, critics and researchers will be able to reason better about language-based media on the Internet. Artists and writers, meanwhile, might just learn a few new techniques to add to their creative palette.
https://gist.github.com/aparrish/509b5cfca74498085b05fe180d93aa3c