link \
NOTE
The concept here is intriguing, more so than this exploratory result.
What differences exist between pages in books? Are there reliable markers to designate a page in the beginning vs an end page?
Maarten Sap research:
neural language model (GPT) does better predicting the next sentence in imagined stories than in recollected stories about biographical events. The authors persuasively interpret this as a sign that imagined stories have been streamlined by a process of “narrativization.”
Why fiction might be more/less predictable:
Fiction is governed by plot conventions, so of course it makes sense that it’s predictable! But an equally intuitive argument could be made that fiction entertains readers by baffling and eluding their expectations about what, specifically, will happen next. Perhaps it ought to be less predictable than nonfiction?
Ted used BERT model to assess pairs of sentences in small set of 32 biographies and 32 novels. Then used BERT to judge probability one sentence would likely follow the other.
BERT is unruffled when Pride and Prejudice morphs into Flatland. As long as each sentence picks up some discursive cue from the one before, BERT perceives the pairs as plausibly connected.
What is a unit of prose that will allow for reading surprise?
Given two passages from a random book, can we predict which came first
Since the two passages may be separated by a hundred-odd pages, our model clearly isn’t registering any logical relationships between events. Instead, it’s probably relying on patterns described in previous work by David McClure and Scott Enderle. McClure and Enderle have shown that there are strong linguistic gradients across narrative time in fiction. References to witnesses, guilt, and jail, for instance, tend to occur toward the end of a book (if they occur at all).
shift:
indefinite articles appear early in a book, when “a mysterious old man” enters “a room.” A few pages later, he will either acquire a name or become “the old man” in “the room.”
At that scale, fiction may be more volatile than nonfiction is. I don’t yet know why! We could speculate that this has something to do with an imperative to surprise the reader—but it might also be as simple as the alternation of dialogue and description, which creates a lot of rapid change in the verbal texture of fiction