Jeffrey M. Binder

Sentence-level Markov model (or, reconstructing Moby-Dick using a neural network)

4

I split each chapter of _Moby-Dick_ into sentences, then used a neural network to try to guess what order the sentences should appear in. I call the result [_Mboy-Dcki_](https://raw.githubusercontent.com/jeffbinder/sentence-level-markov/master/mboydcki.txt). This...

Banalified Moby-Dick

4

I am using the BERT language model to banalify the text of Moby-Dick—that is, to replace Melville's rich language with sentences that better conform to the model's expectations. I'm employing...

I've recently been developing [PromptArray](https://github.com/jeffbinder/promptarray), a syntax for designing ensembles of multiple prompts for neural text generators like GPT-2, tied together with operators like "and" and "not" that alter how...