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

Mistral OCR

mistral.ai

Post reply on HN
Print view View original

421–430 of 450 posts

Re: Mistral OCR

#421

Post by pbhjpbhj »

raffraffraff wrote: post #382
layer8 wrote: post #281

Earlier quoted context omitted.

> This is perfect! Just a nit, but I wouldn’t call it perfect when using U+25CB ○ WHITE CIRCLE instead of what should be U+00BA º MASCULINE ORDINAL INDICATOR, or alternatively a superscript “o”. These are https://fr.wikipedia.org/wiki/Adverbe_ordinal#Premiers_adver... . There’s also extra spaces after the “1607” and around the hyphen in “Diane-Henriette”. Lastly, U+2019 instead of U+0027 would be more appropriate for…

It feels like, after the OCR step there should be language and subject matter detection, with a final sweep with a spelling / grammar checker that has the right "dictionary" selected. (That, right there, is my naivety on the subject, but I would have thought that the type of problem you're describing isn't OCR but classical spelling and grammar checking?)

Not unrelated - OneNote 'copy text from image' has started producing lots of incorrect OCR results, but they're all non-words.

For example, from a clear image of a printed page (in a standard font), it will give me 'cornprising' instead of 'comprising'; 'niatter' instead of 'matter'. Excepting the spell-check underline they'd be hard to spot as with relatively tight kerning all the errors look like the originals.

I'm surprised as 1) I've not had these sorts of errors before, 2) they're not words, and words must be heavily weighted for in the OCR engine (I'd have thought).

Re: Mistral OCR

#424

Post by devmor »

notepad0x90 wrote: post #419
devmor wrote: post #291

Earlier quoted context omitted.

No, I fully understand. I am saying that this type of system, that deprives the user of problem solving, is itself a problem. A detriment to the very essence of human intelligence.

I just look at it as allowing the user to focus on problems that aren't already easily solved. Like using a calculator instead of calculating manually on paper.

But the scenario you described is one in which you need an equation explained to you. That is exactly the kind of scenario where it's important to do the calculation yourself to understand it.

If you are expecting problems to be solved for you, you are not learning, you're just consuming content.

Re: Mistral OCR

#425

Post by ein0p »

Could anyone suggest a tool which would take a bunch of PDFs (already OCR-d with Finereader), and replace the OCR overlay on all of them, maintaining the positions? I would like to have more accurate search over my document archive.

Re: Mistral OCR

#426

Post by bfors »

netdevphoenix wrote: post #402
vikp wrote: post #289

I ran a partial benchmark against marker - https://github.com/VikParuchuri/marker . Across 375 samples with LLM as a judge, mistral scores 4.32, and marker 4.41 . Marker can inference between 20 and 120 pages per second on an H100. You can see the samples here - https://huggingface.co/datasets/datalab-to/marker_comparison... . The code for the benchmark is here - https://github.com/VikParuchuri/marker/tree/master/ben…

LLM as a judge? Isn't that a potential issue? You are assuming the LLM judge is reliable. What evidence do you have to assure yourself or/and others that it is reasonable assumption

Perhaps they already evaluated their LLM judge model (with another LLM)

Re: Mistral OCR

#429

Post by raffraffraff »

layer8 wrote: post #408
raffraffraff wrote: post #382

Earlier quoted context omitted.

It feels like, after the OCR step there should be language and subject matter detection, with a final sweep with a spelling / grammar checker that has the right "dictionary" selected. (That, right there, is my naivety on the subject, but I would have thought that the type of problem you're describing isn't OCR but classical spelling and grammar checking?)

It’s OCR because the wrong characters are being recognized. This is not about fixing spelling or punctuation mistakes present in the source image, it’s that errors are being introduced, due to a lack of accuracy of this OCR with regard to punctuation and typography. The punctuation errors are not different in principle from the case of the OCR producing a misspelled word that wasn’t misspelled in the image being OCRe…

> A subsequent cleanup pass that fixes grammar/spelling errors, as you propose, wouldn’t be appropriate when the goal is to faithfully reproduce the original text

I suppose that depends on why it's wrong. Did the model accurately read a real typo in the image or did it incorrectly decipher a character? If a spelling & grammar pass fixes the latter, isn't it valid?

Re: Mistral OCR

#430

Post by prats226 »

applgo443 wrote: post #316

What's the simple explanation for why these VLM OCRs hallucinate but previous version of OCRs don't?

Traditional OCR's usually have detection + recognition pipeline. So they will detect every word and then try to predict the text for every word. Errors obviously can happen in both parts, eg some words not detected which will get missed from output. Or word recognized incorrectly which is also common and more comparable to hallucination. However give its trained to work only on a small patch, accuracy is often higher. Comparing this to VLM's, they are looking at entire image/context and auto-regressively generating tokens/text which can also have lot of language bias, hence hallicinations.
Post reply on HN