Slashdot Mirror

← Back to Stories (view on slashdot.org)

AI May Have Finally Decoded the Mysterious 'Voynich Manuscript' (gizmodo.com)

Posted by BeauHD on from the shrouded-in-secrecy dept.

An anonymous reader quotes a report from Gizmodo: Since its discovery over a hundred years ago, the 240-page Voynich manuscript, filled with seemingly coded language and inscrutable illustrations, of has confounded linguists and cryptographers. Using artificial intelligence, Canadian researchers have taken a huge step forward in unraveling the document's hidden meaning. Named after Wilfrid Voynich, the Polish book dealer who procured the manuscript in 1912, the document is written in an unknown script that encodes an unknown language -- a double-whammy of unknowns that has, until this point, been impossible to interpret. The Voynich manuscript contains hundreds of fragile pages, some missing, with hand-written text going from left to right. Most pages are adorned with illustrations of diagrams, including plants, nude figures, and astronomical symbols. But as for the meaning of the text -- nothing. No clue. For Greg Kondrak, an expert in natural language processing at the University of Alberta, this seemed a perfect task for artificial intelligence. With the help of his grad student Bradley Hauer, the computer scientists have taken a big step in cracking the code, discovering that the text is written in what appears to be the Hebrew language, and with letters arranged in a fixed pattern. To be fair, the researchers still don't know the meaning of the Voynich manuscript, but the stage is now set for other experts to join the investigation. The researchers used an AI to study "the text of the 'Universal Declaration of Human Rights' as it was written in 380 different languages, looking for patterns," reports Gizmodo. Following this training, the AI analyzed the Voynich gibberish, concluding with a high rate of certainty that the text was written in encoded Hebrew."

The researchers then entertained a hypothesis that the script was created with alphagrams, words in which text has been replaced by an alphabetically ordered anagram. "Armed with the knowledge that text was originally coded from Hebrew, the researchers devised an algorithm that could take these anagrams and create real Hebrew words." Finally, "the researchers deciphered the opening phrase of the manuscript" and ran it through Google Translate to convert it into passable English: "She made recommendations to the priest, man of the house and me and people." The study appears in Transactions of the Association of Computational Linguistics .

9 of 203 comments (clear)

  1. "Finally Decoded" by Anonymous Coward · · Score: 5, Insightful

    STOP using this phrase in each bi-weekly story about this book only to say at the bottom of each article it "isn't really decoded".

    It's "decoded" when the text is readable.

  2. Re:Indian ... not hebrew by beep54 · · Score: 3, Insightful

    Citations sorely needed...

  3. Lololololol by bluegutang · · Score: 5, Insightful

    Failing to find any Hebrew scholars who could help validate their findings, the researchers eventually resorted to using Google Translate,

    (Source)

    This "research" is a joke.

    1. Re:Lololololol by quantaman · · Score: 4, Insightful

      Failing to find any Hebrew scholars who could help validate their findings, the researchers eventually resorted to using Google Translate,

      (Source)

      This "research" is a joke.

      Why? Because the Hebrew scholars didn't want to participate?

      Google Translate botches modern languages. The fact that running their results through Google Translate gave them meaningful output suggests they have real data.

      --
      I stole this Sig
    2. Re:Lololololol by bluegutang · · Score: 3, Insightful

      But they didn't get meaningful output. They got "She made recommendations to the priest, man of the house and me and people". This makes little sense as the first line of a book on herbology. This is AFTER "making a couple of spelling corrections" (how many is a couple?) and AFTER "de-anagraming" every single word (i.e. arbitrary picking one of the thousands of permutations of letters in the word). Not to mention that Hebrew is written without vowels, so any string of several characters is as likely as not to be a word.

      When I was in high school I used a script to find dictionary anagrams of my name and my friends' name. A few of the anagrams looked pretty cool. Did they have any deeper meaning? Of course not. This is basically the same methodology.

  4. Voynich Manuscript is obviously an elaborate prank by pezpunk · · Score: 4, Insightful

    you would think over time people would become less gullible, not more.

    and sure, if you train an AI long and hard enough, it will probably be able to tickle out something that looks like meaning from that nonsense. just like if you train an AI to see dogs, it can identify weird dogs in literally any image.

    https://www.washingtonpost.com...

    --
    i could live a little longer in this prison
  5. One Line by NicknameUnavailable · · Score: 4, Insightful

    Is proof this is a fake. They ran their algorithm, got something almost sensible for the first sentence, and the rest was total gibberish but they needed to publish.

  6. XKCD uncovered its meaning long ago by Opportunist · · Score: 5, Insightful

    https://xkcd.com/593/

    It is obvious when you think about it...

    --
    We used to have a Bill of Rights. Now, with the rights gone, all we have left is the bill.
  7. Re:Indian ... not hebrew by Anonymous Coward · · Score: 0, Insightful

    That's ... not NORTH America you shitflooding trolling idiot.