recentpopularlog in


« earlier   
facebookresearch/unlikelihood_training: Neural Text Generation with Unlikelihood Training
Neural Text Generation with Unlikelihood Training. Contribute to facebookresearch/unlikelihood_training development by creating an account on GitHub.
nlp  text 
yesterday by geetarista
Svgbob Editor - Convert your ascii diagram scribbles into happy little SVG
"It uses a which are combination of characters readily available on your keyboards."
design  text  tool 
2 days ago by marshallim
Create a Random Generator ― ⚅
"Perchance is a platform for creating and sharing random text generators. To create a random generator you simply create lists which reference other lists:"
generator  text 
3 days ago by marshallim
Using Metadata as the Foundation for a Government-Wide FOIA Library | OIP | Department of Justice
The Justice Department’s Open Government Plan version 2.0 (PDF) announced a variety of new Department initiatives concerning the administration of the Freedom of Information Act (FOIA). A key initiative of this plan was the development of metadata standards that would “facilitate the ability of interested persons to search and retrieve documents across websites and disparate record keeping systems.” The plan called for the Office of Information Policy (OIP) to issue guidance for developing metadata standards in the posting of FOIA documents.
foia  metadata  machine_learning  text  data  analysis 
3 days ago by skome
Plain Text Editing Markup for Humans Get the Toolkit Visit us on Github
What is CriticMarkup?

CriticMarkup is a way for authors and editors to track changes to documents in plain text. As with Markdown, small groups of distinctive characters allow you to highlight insertions, deletions, substitutions and comments, all without the overhead of heavy, proprietary office suites.
markdown  text  writing 
3 days ago by newfirewithin
Text Mechanic – Text Manipulation Tools
Welcome to! Simple, single task, browser based, text manipulation tools.
3 days ago by newfirewithin
GPT-2 and the Nature of Intelligence
"known as empiricism, takes the position that hardly any innateness is required, and that learning and experience are essentially all that is required in order to develop intelligence. On this "blank slate" view, all intelligence is derived from patterns of sensory experience and interactions with the world.

In the days of John Locke and Immanuel Kant, all of this was speculation.

Nowadays, with enough money and computer time, we can actually test this sort of theory, by building massive neural networks, and seeing what they learn."
gpt2  ai  ml  work  data  text  generative 
3 days ago by tristanf
Workshop on Open Citations and Open Scholarly Metadata
About 500 million open bibliographic citations are available on the web. via Pocket
citation  standards  text  workshop 
4 days ago by kintopp

Copy this bookmark:

to read