This Jupyter notebook from the National Library of Scotland has a section on
how to evaluate OCR accuracy under the Data Cleaning chapter.
You might also check out the 'fastwer' package described in this article. I
have not used myself so cannot attest to it.
Sarah Swanz
University o
to Github repo with code)
Sarah
On Sep 3, 2021, 10:20 AM -0500, Sarah Swanz , wrote:
> This Jupyter notebook from the National Library of Scotland has a section on
> how to evaluate OCR accuracy under the Data Cleaning chapter.
>
> You might also check out the 'fastwer' pac
organization — not individual author(s) — is the authorial unit.
Tl;dr: It means a lot less metadata about individual authors and complicated
user authorization levels.
There were some other minor flaws, but that did it for us.
Sarah Swanz
On Apr 27, 2023, 9:56 AM -0500, Jenna Jordan , wrote
Similarly, CrossRef requires that DOIs link to landing pages and not the
content file directly.
This is their rationale:
https://www.crossref.org/documentation/member-setup/creating-a-landing-page/
Sarah Swanz
School of Information, MSc ’18
University of Michigan, Ann Arbor
On Feb 15, 2024 at 2
;s a field for
Alternative Identifiers.
Publishing in 2 repos is not the same as publishing the same article in two
journals. A better analogy is having a book in more than one library.
Sarah Swanz
Digital Humanities Librarian & Data Curator
Washington University in St Louis
On Mar 11, 2
