Sentence-level Markov model (or, reconstructing Moby-Dick using a neural network) about 2018 HOT 4 OPEN

MBOY-DCKI;
OR, THE WHEAL.
BY
HERMAN MELVILLE,
AND A NEURAL NETWORK

CHAPTER 1. Loomings.

Call me Ishmael. Go visit the Prairies in June, when for scores on scores of miles you wade knee-deep among Tiger-lilies--what is the one charm wanting?--Water--there is not a drop of water there!

Chief among these motives was the overwhelming idea of the great whale himself. He thinks he breathes it first; but not so.

Circumambulate the city of a dreamy Sabbath afternoon. With a philosophical flourish Cato throws himself upon his sword; I quietly take to the ship. Strange! here come more crowds, pacing straight for the water, and seemingly bound for a dive.

from 2018.

from 2018.

Thanks for sharing this!

The two approaches could possibly be combined by running the neural network on phrases rather than sentences. The training script should work without modification on any linguistic unit (phrases, clauses, paragraphs, etc.)—the corpus just has to be prepared differently. Doing it at the phrase level might make the strangeness more immediate because you would have to read fewer words on average before getting to something that differs from the original text. I'm not sure how well the particular model I used would do at assembling phrases into syntactically correct sentences, though.

from 2018.

Just for reference, links to the two novels:

• Original Method (trained on the Wright American Fiction corpus) - Mboydcki

• Alternative Method (trained on the Moby Dick corpus) - Mobydcik

from 2018.