Hacker News Board Hacker News, browsed like a classic message board
Live data from Hacker News

Can you read this cursive handwriting? The National Archives wants your help

smithsonianmag.com

Post reply on HN
Print view View original

211–220 of 267 posts

Re: Can you read this cursive handwriting? The National Archives wants your help

#211

Post by BugsJustFindMe »

CamperBob2 wrote: post #209
BugsJustFindMe wrote: post #203

Earlier quoted context omitted.

> Did it correctly identify the language as Old French, at least Yes! But that's the easy part. :) > I was talking about OCR'ing modern English cursive handwriting Yeah, see, I think that's a very narrow expectation. Archive paleography is substantially broader than that. I'm not saying that the tools are useless, but they're often still not better than humans directing focused care and attention. > o1-pro, on the ot…

The technique of pitting one model against another is usually pretty effective in my experience. If Gemini 2.0 Advanced and o1-pro agree on something, you can usually take it to the bank. If they don't, that's when human intervention is necessary, given the lack of additional first-rank models to query. (Edit: 1682 versus 1692 being a great example of something that a tiebreaker model could handle.) It seems likely t…

> I can't agree that this type of content is relevant when discussing straightforward OCR tasks on modern languages.

1682 is a number though, language independent, and you noted it as being extremely obvious to a human, even one who can't read any of the other language. So I do think the tools are useful, but people probably still need to be there for now until better models for this are made that stop getting especially obvious parts wrong.

Re: Can you read this cursive handwriting? The National Archives wants your help

#213

Post by astura »

dahart wrote: post #173
electricant wrote: post #114

Earlier quoted context omitted.

Let me disagree. IMHO cursive is faster than print once you get the hang of it. However my point is valid for print too I guess. Regarding time saved and the fact that they are two different systems, I don't get it. Time saved for what? They are not so different, cursive is built on top of print, just optimized for not lifting the pen from the paper too often (hence it is supposedly faster to write).

> However my point is valid for print too I guess. What do you mean? You asked how kids can write without learning cursive, and print is the answer how. What is your point about print? Cursive might be faster for an experienced writer (though Google tells me that claim is debatable), but it takes a long time to get there. I learned cursive as a child, used it for years, and it was never faster than printing, it was m…

>Cursive might be faster for an experienced writer (though Google tells me that claim is debatable), but it takes a long time to get there. I learned cursive as a child, used it for years, and it was never faster than printing, it was much slower.

Cursive probably made sense at a time when everyone was writing with quill pens.

Re: Can you read this cursive handwriting? The National Archives wants your help

#214

Post by thaumasiotes »

ugh123 wrote: post #97
varenc wrote: post #68

Earlier quoted context omitted.

My guess is because it’s the Smithsonian, they’re just not willing to trust an LLM’s transcription enough to put their name on it. I imagine they’re rather conservative. And maybe some AI-skeptic protectionist sentiments from the professional archivists. Seems like it could change with time though.

> My guess is because it’s the Smithsonian, they’re just not willing to trust an LLM’s transcription enough to put their name on it. I imagine they’re rather conservative I expect thats a common theme from companies like that, yet I don't think they understand the issue they think they have there. Why not have the LLMs do as much work as possible and have humans review and put their own name on it? Do you think they…

> Why not have the LLMs do as much work as possible and have humans review and put their own name on it?

That's not a good way to improve on the accuracy of the LLM. Humans reviewing work that is 95% accurate are mostly just going to rubber-stamp whatever you show them. This is equally a problem for humans reviewing the work of other humans.

What you actually want, if you're worried about accuracy, is to do the same work multiple times independently and then compare results.

Re: Can you read this cursive handwriting? The National Archives wants your help

#215

Post by jncfhnb »

BugsJustFindMe wrote: post #169
tedunangst wrote: post #63

Earlier quoted context omitted.

Can someone please post a sample of one of these images that can only be read by a human for us naive OCR believers to see?

I've posted these above, but I'll give you your own copy because the bits are free. Does your OCR work on these? Mine sadly doesn't. But if yours does, then I'll switch to it. https://imgur.com/a/CDU6Lgs

The problem statement was text that random humans can read and OCR cannot.

If you want to provide a good faith answer at least make it English. I assume this is French but it’s obviously much harder to evaluate on both ends when you’re mixing up the language.

Re: Can you read this cursive handwriting? The National Archives wants your help

#216

Post by thaumasiotes »

enlightens wrote: post #170
morning-coffee wrote: post #164

Earlier quoted context omitted.

> Like if this is a crowdsourcing project... I'm confused by what you're asking. Are you asking me to like (upvote) your comment if this is a crowdsourcing project? Don't we already know it is a crowdsourcing project?

The use of the word “like” here could be replaced with the word “so” “So if this is a crowdsourcing project…” Like is serving as an indication that someone else approximately said the phrase it introduced, in a way often associated with the “Valley Girl” social dialect but regularly seen outside of it. https://en.wikipedia.org/wiki/Like#As_a_colloquial_quotative

> The use of the word “like” here could be replaced with the word “so”

Correct, but that's not a quotative use of the word. It's a discourse particle. You want to link one subsection down, like as a discourse particle.

https://en.wikipedia.org/wiki/Like#As_a_discourse_particle,_...

Re: Can you read this cursive handwriting? The National Archives wants your help

#217

Post by iandanforth »

sandworm101 wrote: post #157
prng2021 wrote: post #137

Earlier quoted context omitted.

Determining whether the latest off the shelf LLMs are good enough should be straight forward because of this: “Some participants have dedicated years of their lives to the program—like Alex Smith, a retiree from Pennsylvania. Over nine years, he transcribed more than 100,000 documents” Have different LLMs transcribe those same documents and compare to see if the human or machine is or accurate and by how much.

This is not an LLM problem. It was solved years ago via OCR. Worldwide, postal services long ago deployed OCR to read handwitten addresses. And there was an entire industry of OCR-based data entry services, much of it translating the chicken scratch of doctor's handwiting on medical forms, long before LLMs were a thing.

Fun fact, convolutional neural networks developed by Yann LeCunn were instrumental in that roll out!

Re: Can you read this cursive handwriting? The National Archives wants your help

#218

Post by thaumasiotes »

rtkwe wrote: post #101
tptacek wrote: post #39

Earlier quoted context omitted.

OK, fair enough, but can you find one in this article that's hard for an LLM? The gnarliest one I saw, 4o handled instantly, and I went back and looked carefully at the image and the text and I'm sold. Like if this is a crowdsourcing project, why not do a first pass with an LLM and present users with both the image and the best-effort LLM pass? Later I signed up, went to the current missions, and they all seem to pos…

One that require additional work beyond simply feeding the image into the model would be this example which is a mix of barely legible hand written cursive and easy to read typed form. [0] Initially 4o just transcribes (successfully) the bottom half of the text and has to be prompted to attempt the top half at which point it seems to at best summarize the text instead of giving a direct transcription. [1] In fact it…

> this example which is a mix of barely legible hand written cursive and easy to read typed form.

> In fact it seems to mix up some portions of the latter half of the typed text with the written text in the portion of it's "transcription" about "reduced and indigent circumstances".

What typed form? What typed text? That image is a single handwritten page, and the writing is quite clean, not "barely legible".† The file related to John Hopper appears to be 59 pages, and some of them are typed, but they're all separate images.

Are you trying to process all 59 pages at once? Why?

I should note that transcription is an excellent use of an LLM in the sense of a language model, as opposed to an "LLM" in the sense of several different pieces of software hooked together in cryptic ways. It would be a lot more useful, for this task, to have direct access to the language model backing 4o than to have access to a chatbot prompt that intermediates between you and the model.

† My biggest problems in reading the page: Cursive n and u are often identical glyphs (both written и), leading me to read "Ind." as "Jud."; and I had trouble with the "roster" at the bottom of the page. What felt weirdest about that was that the crossbar of the "t" is positioned well above the top of the stem, but that can't actually be what tripped me up, because on further review it's a common feature of the author's handwriting that I didn't even notice until I got to the very end of the letter. It's even true in the earlier instance of "Roster" higher up on the page. So my best guess is that the "os" doesn't look right to me.

I misread 1758 as 1958, too, but hopefully (a) that kind of thing wears off as you get used to reading documents about the Revolutionary War; and (b) it's a red flag when someone who died in 1838 was born in 1958 according to a letter written in 1935.

Re: Can you read this cursive handwriting? The National Archives wants your help

#219

Post by tptacek »

ellen364 wrote: post #103
tptacek wrote: post #39

Earlier quoted context omitted.

OK, fair enough, but can you find one in this article that's hard for an LLM? The gnarliest one I saw, 4o handled instantly, and I went back and looked carefully at the image and the text and I'm sold. Like if this is a crowdsourcing project, why not do a first pass with an LLM and present users with both the image and the best-effort LLM pass? Later I signed up, went to the current missions, and they all seem to pos…

> Like if this is a crowdsourcing project, why not do a first pass with an LLM and present users with both the image and the best-effort LLM pass? Possibly for the reason that came up in your other post: you mentioned that you spot checked the result. Back when I was in historical research, and occasionally involved in transcription projects, the standard was 2-3 independent transcriptions per document. Maybe the Nat…

You get that I'm not saying they should just commit LLM outputs as transcriptions, right?

Re: Can you read this cursive handwriting? The National Archives wants your help

#220

Post by tptacek »

vintermann wrote: post #123
tptacek wrote: post #39

Earlier quoted context omitted.

OK, fair enough, but can you find one in this article that's hard for an LLM? The gnarliest one I saw, 4o handled instantly, and I went back and looked carefully at the image and the text and I'm sold. Like if this is a crowdsourcing project, why not do a first pass with an LLM and present users with both the image and the best-effort LLM pass? Later I signed up, went to the current missions, and they all seem to pos…

I don't know about this project, but I can easily find thousands of images that gpt-4o can't read, but a human expert can. It can do typed text excellently, antika-style cursive if it's very neat, and kurrent-style cursive never.

For straightforward reasons, I am commenting on this project, not the space of all possible projects. I did try, once, to get 4o to decode the Zodiac Killer's message. It didn't work.
Post reply on HN