Unsupervised joke generation from big data • Hacker News Board

Re: Unsupervised joke generation from big data

#11

Post by VladRussian2 » Tue, Aug 06, 2013, 5:37 PM UTC

i wonder did anybody try the same for HN comments? what would be the karma?

Re: Unsupervised joke generation from big data

#12

Post by grrrando » Tue, Aug 06, 2013, 5:37 PM UTC

Can't we just study @Horse_ebooks?

Re: Unsupervised joke generation from big data

#13

Post by mjn » Tue, Aug 06, 2013, 5:42 PM UTC

blt wrote: post #9

Kapura wrote: post #6

"I like my relationships like I like my source, open I like my coffee like I like my war, cold I like my boys like I like my sectors, bad" These are the funny jokes. Enthusiasm tempered.

Their joke model misses one thing: each noun has to be commonly used in the phrase "I like my ". People often say "I like my coffee black" but nobody ever says "I like my source open." I think that is why they sound weird. But I like the off-kilter unexptectedness.

For jokes in this pattern, there's a somewhat more hard-coded twitter bot that I think does a better job: https://twitter.com/ilikelikeilike

It does jokes of the form "I like my like I like my : , , [and not] ".

noun1 is taken from a hand-coded list (hookups, fellas, lovers, spouses, etc.). noun2 is chosen randomly. Then the adjectives are just the top three adjectives found preceding noun2 in a corpus.

So for example,

    I like my men like I like my banking: inefficient, shadow, not shady.

'men' was chosen from the hard-coded list. 'banking' was just a random noun. "inefficient banking", "shadow banking", and "shady banking" are common phrases in the corpus, so those three adjectives were chosen.

Re: Unsupervised joke generation from big data

#14

Post by darkstalker » Tue, Aug 06, 2013, 5:51 PM UTC

grrrando wrote: post #12

Can't we just study @Horse_ebooks?

Most twitter bots use Markov chains

Re: Unsupervised joke generation from big data

#15

Post by kevincennis » Tue, Aug 06, 2013, 5:53 PM UTC

I like this part:

"This Rank OF Likelihood (ROFL)"

Re: Unsupervised joke generation from big data

#16

Post by kevincennis » Tue, Aug 06, 2013, 5:55 PM UTC

VladRussian2 wrote: post #11

i wonder did anybody try the same for HN comments? what would be the karma?

I wrote a Markov Chain HN comment generator a few months ago. I'd say a solid 70% of them were pretty funny.

Re: Unsupervised joke generation from big data

#17

Post by xerophyte12932 » Tue, Aug 06, 2013, 5:56 PM UTC

I considered working on this once. Especially "comeback" generation. If you look at the comments (or replies to comments) on 9GAG, most of them are pretty generic and follow some basic rules. I figure even a computer can learn to make them.

Re: Unsupervised joke generation from big data

#18

Post by Groxx » Tue, Aug 06, 2013, 6:11 PM UTC

33% might be a bit generous for humans.

Re: Unsupervised joke generation from big data

#19

Post by jere » Tue, Aug 06, 2013, 6:20 PM UTC

If you want a steady stream of this kind of thing, check out the following twitter bot: https://twitter.com/ilikelikeilike

Darius Kazemi writes a lot of twitter bots and I find @AmIRiteBot pretty funny (if only in a it's so bad it's good way): https://twitter.com/amiritebot

For example: #YouDontKnowWhatStruggleIsIf? More like You Dont Know What Snuggle Is If, amirite?

Re: Unsupervised joke generation from big data

#20

Post by dorkrawk » Tue, Aug 06, 2013, 6:22 PM UTC

I would love to look at the code behind this work.