miniblog.

← Back to all posts
May 10, 2017 at 05:39
Google has open sourced their NLP parser: https://research.googleblog.com/2016/05/announcing-syntaxnet-worlds-most.html (includes some great examples of sentences that are hard for machines)
Announcing SyntaxNet: The World’s Most Accurate Parser Goes Open Source
Announcing SyntaxNet: The World’s Most Accurate Parser Goes Open Source
Posted by Slav Petrov, Senior Staff Research ScientistAt Google, we spend a lot of time thinking about how computer systems can read and understand...

Related Posts

Jul 25, 2020 at 17:38
I think JSON vs XML is a strange dichotomy. Both can be processed by machines, but they're very different. I've seen XML work really well for dictionary data. You want to mark up text: A dog is a domesticated <group>animal</group>. In other words JSON : CSV :: XML : HTML.
Jun 28, 2020 at 05:31
@bamfic Lisp Machines had hardware supported tagged pointers, but I'm not aware of other features. Nonetheless, the ability to add custom hardware for your programming model worked out really well for them :)
Jan 16, 2020 at 10:16
It's hard to get developers to pay for tools. I think the problem is that computers are incredibly general machines. Once you've worked in programming for a while, it's easy to imagine making a whole range of tools. It's hard to guess the complexity of new domains though.