daniel bigham.ca

Semantics in Generative Grammar
October 12, 2015

I'm reading this book right now:

http://ca.wiley.com/WileyCDA/WileyTitle/productCd-0631197133,subjectCd-PLD0.html

So far I'm quite enjoying it. Wish I had found resources like this a few years ago, but still good for me to read.

Generating Almost Gibberish
October 12, 2015

An interesting thing I saw today:
http://www.relativelyinteresting.com/the-labyrinthine-library-of-babel/

Kind of silly, but after some further thought, it would be interesting if you created a semantic and syntactic model of the world that was rich enough such that you could run a "parser" backwards and generate sentences that were both semantically and grammatically sound, and yet random... and then to use a probabilistic model to generate a second sentence based on the first, and so on and so forth, until you had written an entire page.

If your system was strong enough, then it might be the case that 1 out of 1,000,000 generate pages would be a bit creepy in terms of its sensibility, right?

As it stands, this 100% random approach comes off as 1% interesting and 99% "sigh".

Technology Stalled?
September 22, 2015

http://www.technologyreview.com/qa/530901/technology-stalled-in-1970/

What I liked about this article most was the sentiment that there is a bias against taking the significant risks required to really push things to the next level. For the last number of years I have felt somewhat held back to really explore what seem to be quite deep and promising ideas. Admittedly, following those trails could lead to failure, but it seems well worth the risk given possible outcomes.

Incremental approaches do seem very wise. I don't want to knock incremental progress. But I think Peter Thiel is on to something here.

One theory is that as the world becomes more and more factored towards a "winner takes all" context, the more it makes sense to take big risks that have enormous potential payoffs. Conversely, the less it makes sense to have a bunch of conservative companies all making tepid incremental progress.

older >>