The Monkey Brain
Building a municipal land use code search engine using a graph of word embeddings

I published this blog post about a project I did with OpenCounter to make a search engine for municipal land use codes: https://blog.opencounter.com/how-opencounter-designed-a-use-code-search-engine-for-local-governments-9e3f845516ee.

Editing this post now in December 2018, what is interesting looking back is how hard I was attempting to overcome the Euclidean nature of these word embeddings. See this blog post from Stanford for a nice overview of some recent results that have been pouring out of the machine learning community, where they are discovering useful ways of using hyperbolic space to represent graphs and networks instead.

Posts

The Monkey Brain is Sam Zhang's blog of weird datasets and mathematical curiosities.

You can try to read this through an Atom-compatible feed reader, but the posts often rely on embedded HTML and Javascript. For the adventurous, here is the feed.xml.

the zoo
github
sam.zhang.fyi/