Earlier quoted context omitted.
If it helps, here's the full paragraph: “We’ll send the infantwy down by the swamps,” Denísov continued. “They’ll cweep up to the garden; you’ll wide up fwom there with the Cossacks”—he pointed to a spot in the forest beyond the village—“and I with my hussars fwom here. And at the signal shot...”
What are "sramps"?
A kinda okay text generator
31–33 of 33 posts
Re: A kinda okay text generator
#32Earlier quoted context omitted.
Lewis Carrol is actually really fun in just a pure markov chain; usually the diction is sufficient to put someone in the mood for Carrol, which means nobody really expects it to make sense anyways.
One of my favorite parts of Gödel, Escher, Bach was the description of translating Lewis Carroll's Jabberwocky into various languages -- particularly troublesome since the original poem contains few English words to begin with.
I think that just highlights how hard poetry is to translate in general. Carroll picked those words with thoughts to how they sound no less than other poets that restrict themselves to English words.
Translating poetry well where both meaning and sounds are vital can be harder than writing the poem in the first place was.
Re: A kinda okay text generator
#33Earlier quoted context omitted.
Sounds like getting some sort of context free grammar out of it. There is a LR grammar algorithm that is very fast, you could use a Markov chain to generate and then a CFG to verify
Or a CFG to generate at a high level and a Markov chain to fill in the details
Excellent idea. Then it would actually read like language! But uh, how to choose sentence length and which grammars you want?