• The input speed of machines is orders of magnitude faster than humans.

  • So it never occurred to me that there is a need to teach speed reading to machines.

  • But from the rhetorical afterimage perspective, there is an appropriate speed for comprehension, and reading too slowly can hinder comprehension.

  • Machine reading is significantly faster than human reading, but “slow reading” that follows every word

  • Maybe we should have a faster reading.

  • In other words, we should teach machines to read faster.

  • Read the Table of Contents

    • E-books with a table of contents as structured data are easy
    • If not, the tree structure of the table of contents must be ascertained from the text data of the paper
    • The tree structure created is the output
  • Keyword Search

    • Can be done with existing keyword extraction programs
    • What is it about “a quick look and it jumps out at you?”
      • One line of text is entered and keywords are extracted from it.
      • Repeatedly appearing keywords increase cognitive efficiency through priming and jump to the eye.
  • Create a question

    • This is pretty advanced, I don’t know how to make it.
    • What is ?”
    • “What is the relationship between and ?”
  • Create a mind map - Output associative network in a tree structure

  • What would you write in a book if a machine could freely write in Scrapbox?

  • Table of Contents of the book

  • Keywords for the book

  • The questions I had after reading the book and their answers

  • A tree-like associative network about the book’s content

    • itemize

This page is auto-translated from /nishio/機械に速読を教える using DeepL. If you looks something interesting but the auto-translated English is not good enough to understand it, feel free to let me know at @nishio_en. I’m very happy to spread my thought to non-Japanese readers.