Very cool. I actually built an app called "Johnny Mnemonic" around 5 years ago that generated a mnemonic sentence given a list of terms when I was studying for my EMT license. At the time I leveraged a simple n-gram markov model that I based off the publicly available Cornell Movie script database.
I added a couple settings like word order(matters: colors of the rainbow, doesn't matter: bones of the skull), anagram vs sentence, etc. At the time the biggest difficulty wasn't necessarily generating a coherent sentence - it was ensuring the "novelty" of the mnemonic. The less surprising the less likely its going to stick.
Fun little tidbit - by adding a "NSFW" flag - I made it so the markov chain would heavily weight racy/saucy/lewd words. End result, VERY VERY evocative mnemonics that were completely and utterly incapable of being shared.
I added a couple settings like word order(matters: colors of the rainbow, doesn't matter: bones of the skull), anagram vs sentence, etc. At the time the biggest difficulty wasn't necessarily generating a coherent sentence - it was ensuring the "novelty" of the mnemonic. The less surprising the less likely its going to stick.
Fun little tidbit - by adding a "NSFW" flag - I made it so the markov chain would heavily weight racy/saucy/lewd words. End result, VERY VERY evocative mnemonics that were completely and utterly incapable of being shared.
Demo:
https://www.youtube.com/watch?v=MTAbVBOMdbk