[Article] Voynich2Vec: Using FastText Word Embeddings for Voynich Decipherment

[elieD]

It's worth noting that MUSE works great for close enough languages. But we're not aware of any language close to the VMS.
That's why I tried finding one first ( You are not allowed to view links. Register or Login to view. ). They used MUSE with "English, Latin, Greek, Spanish, and Arabic", but that's not enough.
Moreover, vms is probably a verbatim transcript which doesn't help in the comparison with other corpus.
The first step is to find something close enough to the VMS, but we're very far from being there.