Recurrent Neural Net Poetry – Commitment

  Bobby took a deep breath. "Lucas said that Jackie's a horse for a snake. Can you run that by me in street tech?"

  "Certainly. Think of Jackie as a deck, Bobby, a cyberspace deck, a very pretty one with nice ankles." Lucas grinned and Bobby blushed. "Think of Danbala, who some people call the snake, as a program. Say as an icebreaker. Danbala slots into the Jaekie's deck, Jackie cuts ice. That's all."

  Okay," Bobby said, getting the hang of it, "then what's the matrix? If she's a deck, and Danbala's a program, what's cyberspace?"

This is impressive from an AI and machine learning perspective but NLP is one area where I feel there haven't been any fundamental breakthroughs yet as we've seen for images.

Perhaps language is much more complex. Visual processing is present in many animals and so it might be that it's simpler at some level. There are very few animals that have evolved to use language like we do.

So the underlying models must be far more complex than stacking layers of convolutional layers on top of each other.

And compared to the spectacular results in images like Neural style transfer , we're judging these to a very low standard. Here is an actual poem :

“You know how this is:

if I look

at the crystal moon, at the red branch

of the slow autumn at my window,

if I touch

near the fire

the impalpable ash

or the wrinkled body of the log,

everything carries me to you,

as if everything that exists,

aromas, light, metals,

were little boats

that sail

toward those isles of yours that wait for me.” ― Pablo Neruda, The Captain's Verses

This particular sally can be found at http://sfbay-anarchists.org/wp-content/uploads/2012/05/Trurl...

What kind of grammar did you design ?

Do you think we can machine learn the grammar aided by things like word2vec ?

As to multiple meanings, I do not force an interpretation, and the model is simple enough that it does not explicitly disambiguate. Part of the fun for me as an artist is letting the model go where it may, often surprising me when it does.