Article Close

Summary View* This content is illustrative

Article Title

in Category


Here's the bug: the smaller the amount of input text, the better the sentences are that it generates. (Above a certain threshold -- too low, and you just get the input text back.)

(10)

Rate It

Published: 04/19/2021 by Article Author

Detail View* This content is illustrative

Article Title

(10)

  • Add to Twitter
  • Add to Facebook
  • Add to Favorites
  • Category 1 (230)
  • Category 1.1 (200)
  • Category 2 (300)
  • Category 2.2 (230)
Published
04/19/2021 by Article Author
  • Overview
  • Reviews

DadaDodo works rather differently than Dissociated Press; whereas Dissociated Press (which, incidentally, refers to itself as a ``travesty generator'') simply grabs segments of the body of text and shuffles them, DadaDodo tries to work on a larger scale: it scans bodies of text, and builds a probability tree expressing how frequently word B tends to occur after word A, and various other statistics; then it generates sentences based on those probabilities The theory here is that, with a large enough corpus, the generated sentences will tend to be grammatically correct, but semantically random: exterminate all rational thought.



DadaDodo works rather differently than Dissociated Press; whereas Dissociated Press (which, incidentally, refers to itself as a ``travesty generator'') simply grabs segments of the body of text and shuffles them, DadaDodo tries to work on a larger scale: it scans bodies of text, and builds a probability tree expressing how frequently word B tends to occur after word A, and various other statistics; then it generates sentences based on those probabilities The theory here is that, with a large enough corpus, the generated sentences will tend to be grammatically correct, but semantically random: exterminate all rational thought.



DadaDodo works rather differently than Dissociated Press; whereas Dissociated Press (which, incidentally, refers to itself as a ``travesty generator'') simply grabs segments of the body of text and shuffles them, DadaDodo tries to work on a larger scale: it scans bodies of text, and builds a probability tree expressing how frequently word B tends to occur after word A, and various other statistics; then it generates sentences based on those probabilities The theory here is that, with a large enough corpus, the generated sentences will tend to be grammatically correct, but semantically random: exterminate all rational thought.

  • Overview
  • Reviews
Rate It
Wait, Loading...

Comments

Sample