Mysteries Department
Sign inRequest access
MethodsNLP (Blei et al. 2003)Topic model (LDA) of pages, k by held-out perplexity and fixed k=10
Method · NLP (Blei et al. 2003)

Topic model (LDA) of pages, k by held-out perplexity and fixed k=10

Nlp (blei et al. 2003)Version 1.0Licence MIT18 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 18 runs · 6 shown

RunMysteryMeasuredResultAgainstDate
RUN-195VoynichMean max theta0.688Latin 0.682 · slot 0.894 · shuffled 0.90222 Oct
RUN-194VoynichBifolio z2.59Latin 0.61 · slot 1.55 · shuffled -1.822 Oct
RUN-193VoynichClusters follow the quires0.442Latin 0.376 · slot 0.183 · shuffled 0.17422 Oct
RUN-192VoynichClusters follow the scribes0.427Latin 0.214 · slot 0.103 · shuffled 0.09422 Oct
RUN-191VoynichClusters follow Currier's languages0.442Latin 0.115 · slot 0.088 · shuffled 0.06522 Oct
RUN-190VoynichClusters follow the sections0.441Latin 0.403 · slot 0.146 · shuffled 0.10922 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.