Here's the pdf of the whole book it appeared in: https://ia801405.us.archive.org/1/items/handbookofmathem017893mbp/handbookofmathem017893mbp.pdf …
Anybody have a PDF of “Finitary models of language users” by Miller and Chomsky 1963? HUGELY relevant to the new @openAI work... In meantime, dig what a 4gram model of Shakespeare can do (& risks), in Figure 3.3ff, Chapter 3 of @jurafsky text. https://web.stanford.edu/~jurafsky/slp3/
-
-
- 1 more reply
New conversation -
-
-
The lack of 21-gram models in natural language processing is gravely disturbing!
Thanks. Twitter will use this to make your timeline better. UndoUndo
-
Loading seems to be taking a while.
Twitter may be over capacity or experiencing a momentary hiccup. Try again or visit Twitter Status for more information.