what about poets and writers providing themes and phrases in which to extrapolate.
I feel like it would be possible to generate compelling stories w deep learning. But we would need a proper input space; raw text is not it.
-
-
-
oral poetry with mix match of components for new story? Feed Homer to net and check output...
- Show replies
New conversation -
-
-
This Tweet is unavailable.
-
I honestly think you're vastly underestimating what it takes to write compellingly. AI-complete almost certainly.
- Show replies
-
-
-
for structure: Vladimir Propp? https://en.m.wikipedia.org/wiki/Vladimir_Propp … or Campbell https://en.m.wikipedia.org/wiki/Hero%27s_journey … :)
Thanks. Twitter will use this to make your timeline better. UndoUndo
-
-
-
seq2seq w/ attention. Paired input, output are life experiences, subsequent stories. Should be datasets lying around w those, no?
-
[[realizing the great work you do will all be dust one day],['Ozymandias']]
End of conversation
New conversation -
-
-
Thanks. Twitter will use this to make your timeline better. UndoUndo
-
-
-
I totally agree with you, the machine also needs visual experience, I was working in a similar problem when I proposed the VIEW.
Thanks. Twitter will use this to make your timeline better. UndoUndo
-
Loading seems to be taking a while.
Twitter may be over capacity or experiencing a momentary hiccup. Try again or visit Twitter Status for more information.