Without assuming anything about meaning or trying to decode the mysterious 15th-century Voynich Manuscript, Brian Grant wrote software that analyzed the structure of its inscrutable text to see if it corresponded to what one would expect to find in natural language. "It kinda did," writes Grant.
This project was built as a way to learn — about AI, NLP, and how far structured analysis can get you without assuming what you're looking at. I'm not here to crack the Voynich. But I do believe that modeling its structure with modern tools is a better path than either wishful translation or academic dismissal.
So if you're here for a Rosetta Stone, you're out of luck.
If you're here to model a language that may not want to be modeled — welcome.
Here's the good news for Voynich fans:
The manuscript encodes a structured constructed or mnemonic language using syllabic padding and positional repetition. It exhibits syntax, function/content separation, and section-aware linguistic shifts — even in the absence of direct translation.
The manuscript has not been deciphered, obviously, though there's always a hot new hypothesis.
Previously:
• Multispectral imaging of the Voynich Manuscript
• Voynich Manuscript 'solution' rubbished by experts
• Voynich Manuscript online
• The Voynich Manuscript appears to be a fairly routine anthology of ancient women's health advice
• New Voynich Manuscript reproduction uses new photos, looks great
• Voynich Manuscript partially decoded, text is not a hoax, scholar finds
• Voynich manuscript dated to early renaissance
• Similaries between The Voynich Manuscript and outsider art by people with schizophrenia
