Get the latest tech news

Show HN: I modeled the Voynich Manuscript with SBERT to test for structure


Contribute to brianmg/voynich-nlp-analysis development by creating an account on GitHub.

This started as a personal challenge to figure out what modern NLP could tell us about the Voynich Manuscript — without falling into translation speculation or pattern hallucination. I just wanted to see if something as strange as Voynichese would hold up under real language modeling: clustering, POS inference, Markov transitions, and section-specific patterns. Cluster-to-word mappings are indirect — frequency estimates may overlap Suffix stripping is heuristic and may remove meaningful endings No semantic translation attempted — only structural modeling

Get the Android app

Or read this on Hacker News

Read more on:

Photo of structure

structure

Photo of voynich manuscript

voynich manuscript

Photo of SBERT

SBERT

Related news:

News photo

Amazon Revamps Pay Structure to Further Reward High-Performing Employees

News photo

Evolving OpenAI's Structure

News photo

Portugal’s NOS Plans to Overhaul Structure, Weighs Job Cuts