Markov Me

November 13th, 2013
blog, markov, meta
Facebook today is full of people posting sentences from what-would-i-say which generates new you-ish sentences from your Facebook posting history. Because people don't post that many statuses, it doesn't have too much to work with and has to use a small unigram/bigram model. I like some of the ones it gets for me, but a bigger corpus should help. [1] Feeding all of my blog posts into a simple trigram generator I wrote I get: [1] To select random words I needed to total up how many words I've written here. Apparently that would be 330k. That's kind of a lot.

Comment via: google plus, facebook, substack

Recent posts on blogs I like:

Raffles

I think that raffles are kind of silly, because when you enter a raffle and you don't know what you're going to get, or if you're going to get anything, what's the point? If you pay for your raffle ticket, and you could pay the same amount…

via Anna Wise's Blog Posts September 13, 2026

Air Filters in Schools

My dad went to a conference recently, and when I asked him about what happened there he said it was a conference for people in biosecurity. When I asked him about the different kinds of biosecurity stuff that the different groups did, he said one did air f…

via Lily Wise's Blog Posts September 12, 2026

The One That I Want Another Sister

I want a baby sister or brother. Because I want to play with another kid, and I don't want to play with Josie because she is in preschool and I won't play with her very often. So I want to play with someone very often who is not just two people. …

via Nora Wise's Blog Posts September 5, 2026

more     (via openring)