John Ohno

Results 113 comments of John Ohno

DCGs can generate text based on template rules (see: https://github.com/enkiv2/misc/blob/master/tracery2dcg.py). Since you can inject extra state with semicontext notation & inject calls to traditional goals with {} (see https://www.metalevel.at/prolog/dcg) it...

Embedded prolog helps when you're using the solver for filling in details & doing the broad strokes in an imperative language. If I understand correctly, this is the opposite situation,...

Following grailers also gives a great excuse for surreal events & leaps of logic. It's hard to imagine a generated story that's as strange as the actual story of Parzival....

"Fake Press Coverage" should probably be classified under templates & expansion (since it uses rather complex templating), and "stupid plotto" should probably be classified under "50000 meows" (since it's just...

Nevermind on moving scene/sequel: it's also reasonable to stick it under story compilers. I just didn't see it the first time :) On Thu, Nov 3, 2016 at 8:09 AM...

I'd love to see this! I've found that it's straightforward to match the rhyme and syllable scheme but making a limerick that makes sense grammatically is a lot harder. On...

Awesome! I love working with dreams. On Sun, Nov 13, 2016 at 4:43 PM Kelly [email protected] wrote: > I've written some initial code I'd like to improve upon to generate...

Our own @aparrish wrote [Sea Duck](https://github.com/aparrish/seaduck), a system for generating tracery grammars out of rules about nouns, their properties, and the actions that can apply to them.

Emily Short wrote [a survey of recent academic work in narrative generation](https://emshort.blog/2018/10/16/mailbag-ai-research-on-dialogue-and-story-generation/), some of which may be worth building on.

Wikipedia has themed word-frequency lists: https://en.wiktionary.org/wiki/Wiktionary:Frequency_lists On Thu, Oct 18, 2018 at 1:23 PM Alex Korbonits wrote: > https://fiction.ict.usc.edu/creativehelp/ -- Melissa Roemmele presented > about it in last year's NIPS...