Forgot your password?
typodupeerror
AI

How AI is Unlocking Ancient Texts (nature.com) 52

AI is unlocking ancient texts previously thought unreadable, potentially revolutionizing historical research, according to a Nature article. Neural networks have successfully decoded burned Roman scrolls from Herculaneum, deciphered ancient Chinese oracle bones, and translated vast Korean royal archives.

In a breakthrough achievement, researchers used AI to reveal 16 columns of Greek philosophical text from a charred Herculaneum scroll that had been unreadable for 2,000 years. The technology could help scholars access hundreds more unopened scrolls from Herculaneum and other historical collections worldwide.
This discussion has been archived. No new comments can be posted.

How AI is Unlocking Ancient Texts

Comments Filter:
  • by Anonymous Coward on Wednesday January 01, 2025 @07:05PM (#65055855)

    The one thing everyone knows about current neural net technology is the tendency to "hallucinate".
    If people couldn't read what was there, why do they think the AI got it right?

    • Thats what im thinking, confirmation bias will whitewash this into enhancing the established religious delusions
    • by dfghjk ( 711126 )

      It's not a tendency, it always hallucinates. It's just called a hallucination when you don't like the results.

      The entire term is an excuse, the fact is that AI works the way it works and its "designers" use creative language to suggest that there is merely an occasional problem that will get resolved. No, AI makes shit up always, and sometimes it's particularly bad.

    • This is the proper question to ask because it's the fundamental way of the scientific method.

      So let's start with some basics on your question, and develop some trust in the answer using the burned scrolls, I have no interest in the outcome, I just study a lot so I can ask better questions.

      1) so via radiography we can estimate and or determine the x line of the scroll with y being the depth, and different atomic or chemical signatures
      2) via tangent space of a Riemannian manifold ( I think I said that right,

    • They probably do the same thing that we do in particle physics with machine learning algorithms: measure the performance using some examples that you already know the answer for but which was not part of the training sample. In physics this is typically simulated data where you know what the true physics happening was but for this I'd just hold back some scrolls where humans have already translated them and then feed them into the algorithm and see whether the output matches the human translation.

      You do
    • by quenda ( 644621 )

      Why? A question both obvious and loaded.
      Why is parent assuming they "trust the results"? Even though he has heard of AI hallucination, he seems to stupidly assume the experts have not.
      Classic case of Dunning Kruger.

    • In the case of the burned scrolls it is being used to make the text legible from xrays. The output is going to quickly be determined if it makes sense or not because we can read ancient greek and latin.

    • Per TFA:

      In tests, Ithaca restored artificially produced gaps in ancient texts with 62% accuracy, compared with 25% for human experts. But experts aided by Ithaca’s suggestions had the best results of all, filling gaps with an accuracy of 72%. Ithaca also identified the geographical origins of inscriptions with 71% accuracy, and dated them to within 30 years of accepted estimates.

      So for 2000 years, people could only guess well as to what about 25% of these missing portions would have meant. With modern statistic ("AI") they can produce good guesses 47% better (for total of accurate 71% of the time) or.. just run the system with no human guidance at all and accept a "miss rate" that is 9% worse than when expert supervision is there.

    • Because you seem to have a misunderstanding about AI and the various ways it's used. They're not taking this stuff and plugging it into Chat GPT. They have researcher developers who build custom neural network software to analyze their data. The reason the pop LLMs hallucinate is because they're fed massive amounts of random language or visual data and tasked with generating a response that matches the highest probability of a match. So if that highest probability is 60%, well that's the response you wi

    • LLM's hallucinate - this is a neural Net, the other much more reliable and successful AI, the one that is likely to actually be the future of AI

      They also occasionally hallucinate, but only about the same amount as experts in the highly specific field they net was trained in

    • by RobinH ( 124750 )

      Exactly. Any "reasonable" result would be considered correct, and AI's only strength is producing output that looks reasonable.

      I work with a bunch of tool makers. They have this saying, "nobody calibrates their calipers until it gives you an answer you don't like." If it tells you the part you made is within tolerance, you think, "great". If it says it's out of tolerance, you think, "that can't be right," and you go check it on a calibration block.

  • Making up more bullshit to deceive people about their gods/myths
  • So far, a whole lotta nuttin'.

  • Okay, but how can we trust the Algorithm is actually translating/deciphering the source material correctly?
    • by dfghjk ( 711126 )

      We don't, and that's never mattered before. Translations are always subjective, and correct is defined by whoever wins an argument.

    • by quonset ( 4839537 ) on Wednesday January 01, 2025 @08:08PM (#65056013)
      If you have a problem with AI doing this, don't look into human scholars translating ancient texts. Two of the three major religions can't even come up with an agreement on if Mary was a virgin because of the words used, and one of those religions contradicts itself on who said what about Mary.

      Jewish version [jewishvoice.org].

      Christian version [christianity.com] saying Luke was the one to indicate Mary was a virgin.

      Christian version number 2 [theconversation.com] saying Matthew was the only one to say Mary was pregnant before she had sex with Joseph.

      And then there's the whole homosexual issue which didn't arise until 1946 when someone decided to change the original meaning [imgur.com] of what was (supposedly) written.
      • Mostly a valid point. Ironically though the claim about the verse in Leviticus is wrong if one looks at the Hebrew text of that verse.
      • I would say the Bible can only go wrong, because any translation is still produced with the intent of being used in religious observance, and will therefore be influenced by the views of the organization promoting the translation. It will be hard for anyone doing the job to extract themselves from their own religious background. Here it's the scroll telling the adventures of Bigus Dickus in Herculanum and that won't bring as much bias.

      • And then there's the whole homosexual issue which didn't arise until 1946 when someone decided to change the original meaning [imgur.com] of what was (supposedly) written.

        You kind of detract from your point here. Yes, any time you translate from one language or idiom to another, there is going to be information loss or gain in the output. A 100% translation from one language to another, keeping the meaning, connotation, nuance, etc., the exact same, is very rare. For Biblical and other religious translators, there's a huge debate over word-to-hear literal translations vs a more literary translation vs a more meaning-thematic translation. There's not really a single correct

      • by shilly ( 142940 )

        That first link is *not* to a Jewish site. It does *not* represent a Jewish perspective on the meaning of (the ancient Hebrew word under discussion). That site is run by "Believers in Jesus committed to showing His love and sharing the life-changing message of the Messiah with Jewish people". None of that is a Jewish thing to do.

        An actual Jewish perspective can be found here: https://outreachjudaism.org/al... [outreachjudaism.org]

        Although my personal Jewish perspective is: Christians can believe these texts mean different thing

      • Correction: regarding the word for homosexuality, you are criticizing human scholars by linking to an Imgur image of a post that complains about how a Greek word was wrongly translated and how that changes the meaning of a verse from Leviticus that was actually written in Hebrew. Also, "arseno-koitai" means literally "male-bed" - the meaning has nothing to do with a child.

        While a discussion may be had about the nuances of translating that particular word, I would not use it to show the stupidity of Bible

    • by quenda ( 644621 ) on Wednesday January 01, 2025 @09:11PM (#65056123)

      Before answering, I confess I cheated and actually read TFA.

      "In tests with artificially produced gaps, the model’s top ten predictions included the correct answer 72% of the time, and in real-world cases it often matched the suggestions of human specialists. To improve the results further, Papavassileiou hopes to add in visual data, such as traces of incomplete letters, rather than just relying on the transliterated text. She is also investigating ‘transfer learning’, in which the model applies lessons learnt from one series of tablets to another."

      So the real answer is simply they do not trust the results, not yet. But progress is being made, and the the AI is better than human guesses already.

    • If scanned images / 3d reconstructions are available, scientists in different countries and in the coming decades can run different algorithms and compare the results, until we converge to a consensus on which letters are indeed present on the manuscript, and which were extrapolated carelessly by the algorithm and should be excluded.

    • >> how can we trust the Algorithm
      "Trust me Bro"
      What could go wrong.
      Real answer: you can't.

  • by ndsurvivor ( 891239 ) on Wednesday January 01, 2025 @09:13PM (#65056125) Journal
    The thrust, or the point... I have listened to more than a few podcasts about this. The thing that the article left out is about how new scanning technology can distinguish writing at mm scale, and distinguish inks from non-inks. But, however, we feed these scrolls into scanning equipment, and get thousands of scans that look literally like "ink blots", and how do we with our puny human minds "unravel them" and make sense of them? AI is doing that, but I think the article is under-reporting how important new scanning technology is as well.
    • https://www.npr.org/2024/02/12... [npr.org] A scroll covered by the eruption of Mount Vesuvius has been read for the first time — with the help of artificial intelligence. This is a really interesting podcast!! I think!
      • You will also appreciate the story of Sigurant, the story is in french here: https://www.radiofrance.fr/fra... [radiofrance.fr] and in the following documentary here https://www.youtube.com/watch?... [youtube.com] around 1 hour 14 in, you can see the charred bit of parchment that looks like absolutely nothing, and the same new scanning techs you mentioned going right through, allowing the researcher reconstitute that lost tale (which tells a story of a lost knight and the fire of a dragon by the way, in a fun twist).
  • To drink your Ovaltine.

Behind every great computer sits a skinny little geek.

Working...