The Library of Congress has launched a new crowd-sourced transcription tool
1–10 of 10 posts
Re: The Library of Congress has launched a new crowd-sourced transcription tool
#2"...improving access to handwritten and typed documents that computers cannot accurately translate without human intervention..." Is this true?
Re: The Library of Congress has launched a new crowd-sourced transcription tool
#3It would be cool if they released this as a captcha. I'm sick of teaching Google cars how to drive for free, but this I could get behind.
Re: The Library of Congress has launched a new crowd-sourced transcription tool
#4I feel like they failed to do proper incentive modeling for crowdsourcing (or maybe I just don't understand the target audience).
Recaptcha(v1) also does transcription correction but they incentivize a huge pool of users to help, not because they want to help, but because they need to prove they aren't robots.
Here we need to rely on volunteers? I am not sure if transcribing old documents is rewarding enough for people to do it out of good will. It's not low effort like Folding@home where you can just set and forget. It requires a lot of repetitive and lonely effort!
Re: The Library of Congress has launched a new crowd-sourced transcription tool
#5Very cool! LoC produces incredible work and does the US proud.
Re: The Library of Congress has launched a new crowd-sourced transcription tool
#6"...improving access to handwritten and typed documents that computers cannot accurately translate without human intervention..." Is this true?
yes? OCR technology has come a long way, but there's a lot of cases where it fails badly, including historical (read: non-typed and sometimes damaged) artifacts.
Re: The Library of Congress has launched a new crowd-sourced transcription tool
#7"...improving access to handwritten and typed documents that computers cannot accurately translate without human intervention..." Is this true?
Here's an example of one of the documents if you want to gauge how easy the challenge is:
https://crowd.loc.gov/campaigns/letters-to-lincoln/1830-1839...
There's a lot of academic research (see e.g. https://transkribus.eu/Transkribus/) but that's in progress rather than done.
Re: The Library of Congress has launched a new crowd-sourced transcription tool
#8I feel like they failed to do proper incentive modeling for crowdsourcing (or maybe I just don't understand the target audience). Recaptcha(v1) also does transcription correction but they incentivize a huge pool of users to help, not because they want to help, but because they need to prove they aren't robots. Here we need to rely on volunteers? I am not sure if transcribing old documents is rewarding enough for peop…
Counter example: Wikipedia
Re: The Library of Congress has launched a new crowd-sourced transcription tool
#9"...improving access to handwritten and typed documents that computers cannot accurately translate without human intervention..." Is this true?
Here's an example of one of the documents if you want to gauge how easy the challenge is: https://crowd.loc.gov/campaigns/letters-to-lincoln/1830-1839... There's a lot of academic research (see e.g. https://transkribus.eu/Transkribus/ ) but that's in progress rather than done.
This one is particularly tricky:
https://crowd.loc.gov/campaigns/civil-war-soldiers-disabled-...
A left-handed penmanship contest for soldiers who lost their right arms and were relearning to write. Some of them are remarkably good considering, but some are barely legible.
Re: The Library of Congress has launched a new crowd-sourced transcription tool
#10I feel like they failed to do proper incentive modeling for crowdsourcing (or maybe I just don't understand the target audience). Recaptcha(v1) also does transcription correction but they incentivize a huge pool of users to help, not because they want to help, but because they need to prove they aren't robots. Here we need to rely on volunteers? I am not sure if transcribing old documents is rewarding enough for peop…
I've done it for my own enjoyment. I do logs of historic sea voyages. You never now when you will stumble upon some fascinating content or event. I found a love poem for a dead sweetheart that was written while off the coast of Chile on the author's way to San Francisco in 1849. It was heartbreakingly beautiful.
Monday June 11th In Lat. 9º 54' Long. 119º 12'. Commenced cloudy with refreshing showers. Wind from the W. Rather light.
I felt rather lazy and disagreeable all day. Great washing day for all hands. Thought I should like to roam in the garden of home. Thought of the pleasant warm days. How I used to enjoy myself in looking at the luxuriant growth of trees etc.
Thought of the Sundays with old friends. Thought of my particular female friend F.G.B. who lies now dead & mouldering in that uncharted spot Mount Auburn. Lively girl thou art goen. Mourn thy friends who knew thy good qualities and worth. Time can not efface from my memory thy loveliness.
Lovely girl thou art goen
Yes thy earthly course is run
Friends who knew thee are left to mourn
For thy loss till death is done
On that fair mount thy art laid
Where many a flower had their turn
Kind friends are weeping o'r thee
Gay birds are warbling on thy grave
Return sweet girl, return"
Notes: The word goen occurs repeatedly in this journal. According to the Oxford English Dictionary goen is a form of gone.
F.G.B. is likely Frances G. Blackstock.
Excerpt From: “James White's Journal.” iBooks.