Mysteries Department
Sign inRequest access
MethodsNLP / Copiale-style context clusteringDistributional word classes (PPMI-SVD embeddings, k-means)
Method · NLP / Copiale-style context clustering

Distributional word classes (PPMI-SVD embeddings, k-means)

Nlp / copiale-style context clusteringVersion 1.0Licence MIT5 runsUsed on 1 mystery

How it works

Compared with: Latin of the manuscript's genres, slot-grammar text and the manuscript shuffled across pages, all in the same lines.

Code Python

Download module (.py)methods_ind.pyView source

Runs and results 5 runs

RunMysteryMeasuredResultAgainstDate
RUN-095VoynichNmi class line position0.0164Latin 0.0029 · slot 0.0034 · shuffled 0.000722 Oct
RUN-094VoynichNmi class length0.097Latin 0.094 · slot 0.044 · shuffled 0.05422 Oct
RUN-093VoynichNmi class last letter0.156Latin 0.158 · slot 0.061 · shuffled 0.06522 Oct
RUN-092VoynichNmi class first letter0.177Latin 0.152 · slot 0.084 · shuffled 0.08322 Oct
RUN-091VoynichVocab331.0Latin 310.0 · slot 343.0 · shuffled 347.022 Oct

Applied to

Voynich Manuscript
3 datasetsExploration split, Latin genre texts, ZL3b transcription
Private beta Downloads are for beta members

We're in a private beta while we get things right. Everything here is free to read; downloading datasets, sources and code is open to members for now.

Apply to the betaSign in
It takes a couple of minutes. We'll reply by email.