NewsBot under the hood

We recently wrote about what our NewsBot Chrome extension does today I’m going to add to that and explain how it works behind the scenes. When building this project we approached it as if we were a user of the Lateral API to see what we could build.

How do machines learn meaning?

Computers consist of on/off switches and process meaningless symbols. So how is it that we can hope that computers might understand the meaning of words, products, actions and documents? If most of us consider machine learning to be magic, it is because we don’t yet have an answer to this question. Here, I’ll provide an answer in the context of machines learning the meaning of words. But as we’ll see, the approach is the same everywhere.

You’ll never guess which API documentation tools we use

Today I am going to talk about API documentation tools. Specifically the ones we use at Lateral to create our documentation. Now, I understand if you aren’t enthused by API documentation, I get that. But a lot of people are. I am. People who make APIs are. So maybe you should be too. You don’t want to be left behind not knowing what’s possible with today’s advanced API tools. What would you talk about at conferences? It’d be terrible. Imagine. You’d have no idea. Anyway. Here we go.

The Unknown Perils of Mining Wikipedia

If a machine is to learn about humans from Wikipedia, it must experience the corpus as a human sees it and ignore the overwhelming mass of robot-generated pages that no human ever reads. We provide a cleaned corpus (also a Wikipedia recommendation API derived from it).

Exploring your thoughts with machine learning

Having recently released our TED talks demo we felt another interesting application would be the thoughts of one person. No one fits that description more than Maria Popova’s excellent collection of ideas on her Brain Pickings site. With thoughts on music to philosophy we felt it would be an excellent exploration of how our technology represents thoughts.

TED Talks Visualizer

TED is an awesome platform for ideas, so we thought an interesting experiment would be having our API provide recommendations based on the talks’ transcripts.

Full text search in milliseconds with PostgreSQL

At Lateral we use PostgreSQL to store documents for our visualiser. Each document consists of a text column and a JSON column with meta data inside such as a title, date and URL. We wanted to create a fast search experience for the visualiser that lets you search the full text of documents as well as their titles to quickly find a document to get Lateral recommendations for.