Generating fake whiskey reviews with GPT-2

Posted on Sun 23 June 2019 • Tagged with python, deep learning, natural language • 11 min read

I’ve enjoyed whiskey for a while now, but I can never vocalize all the flavors present in a bottle. I read all these flowery reviews and tasting notes online and I just have no idea how these people come up with descriptions like “caramels, dried peats, elegant cigar smoke, seeds scraped from vanilla beans, brand new pencils, peppercorn, coriander seeds, and star anise”… until now.


Remapping the world with word vectors

Posted on Sat 02 December 2017 • Tagged with natural language, dataviz, d3.js • 10 min read

Everyone is used to the map. Most people could make a reasonable attempt at drawing one from memory (well, sort of). But what would it look like if we positioned the countries not by geographical location, but by our own perceived relationships between them? Armed with Conceptnet Numberbatch, I decided to try just that.


engl_ish: Simulate your language. ish.

Posted on Sat 04 February 2017 • Tagged with python, markov, natural language, open source • 18 min read

Quite a while ago I saw a short film called Skwerl, meant to demonstrate “how English sounds to non-English speakers”. As a native English speaker, watching it is quite surreal. The sounds and accents are totally familiar, and there are definitely words in there that you recognize, but there is no discernible overall meaning whatsoever. It’s actually kind of hard to listen to. All you’ve got to hang onto is that what you’re hearing somehow feels like English. And that’s the point. Skwerl gave me the idea to attempt to create a similar effect, but with reading instead of listening. I wanted to see how English looks to non-English readers. And so I created engl_ish.