Hacker News Board Hacker News, browsed like a classic message board
Live data from Hacker News

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

github.com

Post reply on HN
Print view View original

41–50 of 142 posts

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

#41

Post by patcon »

I see that you're looking for clusters within PCA projections -- You should look for deeper structure with hot new dimensional reduction algorithms, like PaCMAP or LocalMAP!

I've been working on a project related to a sensemaking tool called Pol.is [1], but reprojecting its wiki survey data with these new algorithms instead of PCA, and it's amazing what new insight it uncovers with these new algorithms!

https://patcon.github.io/polislike-opinion-map-painting/

Painted groups: https://t.co/734qNlMdeh

(Sorry, only really works on desktop)

[1]: https://www.technologyreview.com/2025/04/15/1115125/a-small-...

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

#42

Post by nine_k »

InsideOutSanta wrote: post #32
brig90 wrote: post #4

Earlier quoted context omitted.

Yep, that was my takeaway too — the structure feels too consistent to be random, and it echoes known linguistic patterns.

> the structure feels too consistent to be random I don't see how it could be random, regardless of whether it is an actual language. Humans are famously terrible at generating randomness.

The kind of "randomness" hardly compatible with language-like structure could arise from choosing the glyphs according to purely graphical concerns, "what would look nice here", lines being too long or too short, avoiding repeating sequences or, to the contrary, achieving interesting 2D structures in the text, etc. It's not cryptography-class randomness, but it would be enough to ruin the rather well-expressed structures in the text (see e.g. the transition matrix).

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

#43

Post by brig90 »

patcon wrote: post #41

I see that you're looking for clusters within PCA projections -- You should look for deeper structure with hot new dimensional reduction algorithms, like PaCMAP or LocalMAP! I've been working on a project related to a sensemaking tool called Pol.is [1], but reprojecting its wiki survey data with these new algorithms instead of PCA, and it's amazing what new insight it uncovers with these new algorithms! https://patco…

Thanks for pointing those out — I hadn’t seen PaCMAP or LocalMAP before, but that definitely looks like the kind of structure-preserving approach that would fit this data better than PCA. Appreciate the nudge — going to dig into those a bit more.

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

#44

Post by tetris11 »

lukeinator42 wrote: post #24
tetris11 wrote: post #7

UMAP or TSNE would be nice, even if PCA already shows nice separation. Reference mapping each cluster to all the others would be a nice way to indicate that there's no variability left in your analysis

Do you have examples of how this reference mapping is performed? I'm interested in this for embeddings in a different modality, but don't have as much experience on the NLP side of things

Nothing concrete, but you essentially perform shared nearest neighbours using anchor points to each cluster you wish to map to. These form correction vectors you can then use to project from one dataset to another

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

#45

Post by InsideOutSanta »

nine_k wrote: post #42
InsideOutSanta wrote: post #32

Earlier quoted context omitted.

> the structure feels too consistent to be random I don't see how it could be random, regardless of whether it is an actual language. Humans are famously terrible at generating randomness.

The kind of "randomness" hardly compatible with language-like structure could arise from choosing the glyphs according to purely graphical concerns, "what would look nice here", lines being too long or too short, avoiding repeating sequences or, to the contrary, achieving interesting 2D structures in the text, etc. It's not cryptography-class randomness, but it would be enough to ruin the rather well-expressed struct…

>choosing the glyphs according to purely graphical concerns, "what would look nice here", lines being too long or too short, avoiding repeating sequences or, to the contrary, achieving interesting 2D structures in the text

I wouldn't assume that the writer made decisions based on these goals, but rather that the writer attempted to create a simulacrum of a real language. However, even if they did not, I would expect an attempt at generating a "random" language to ultimately mirror many of the properties of the person's native language.

The arguments that this book is written in a real language rest on the assumption that a human being making up gibberish would not produce something that exhibits many of the properties of a real language; however, I don't see anyone offering any evidence to support this claim.

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

#48

Post by thih9 »

(I know nothing about NLP)

Does it make sense to check the process with a control group?

E.g. if we ask a human to write something that resembles a language but isn’t, then conduct this process (remove suffixes, attempt grouping, etc), are we likely to get similar results?

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

#49

Post by Avicebron »

ck2 wrote: post #46

> "New multispectral analysis of Voynich manuscript reveals hidden details" https://arstechnica.com/science/2024/09/new-multispectral-an... but imagine if it was just a (wealthy) child's coloring book or practice book for learning to write lol

> but imagine if it was just a (wealthy) child's coloring book or practice book for learning to write lol

Even if it was "just" an (extraordinarily wealthy and precocious) child with a fondness for plants, cosmology, and female bodies carefully inscribing nonsense by repeatedly doodling the same few characters in blocks that look like the illuminated manuscripts this child would also need access to, that's still impressive and interesting.

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

#50

Post by minimaxir »

jszymborski wrote: post #11
tetris11 wrote: post #7

UMAP or TSNE would be nice, even if PCA already shows nice separation. Reference mapping each cluster to all the others would be a nice way to indicate that there's no variability left in your analysis

When I get nice separation with PCA, I personally tend to eschew UMAP, since the relative distance of all the points to one another is easier to interpret. I avoid t-SNE at all costs, because distance in those plots are pretty much meaningless. (Before I get yelled out, this isn't prescriptive, it's a personal preference.)

PCA having nice separation is extremely uncommon unless your data is unusually clean or has obvious patterns. Even for the comically-easy MNIST dataset, the PCA representation doesn't separate nicely: https://github.com/lmcinnes/umap_paper_notebooks/blob/master...
Post reply on HN