# Gromov-Wasserstein alignment of written-word and Latin co-occurrence spaces

> Problem Track A can't solve: whether there is a word-level map at all. Track A assumes signs inside words; this needs no key and no segmentation, only…

Source: https://mysteriesdept.com/methods/MTH0DCF1JFCRDXQ/gromov-wasserstein-alignment-of-written-word-and-latin-co  
Publisher: Mysteries Department  
Licence: CC BY 4.0 (credit Mysteries Department and link the page)  

---

[Methods](https://mysteriesdept.com/methods)[Machine learning (optimal transport)](https://mysteriesdept.com/methods?kind=machine-learning-and-simulation)Gromov-Wasserstein alignment of written-word and Latin co-occurrence spaces

Method · machine learning (optimal transport)

# Gromov-Wasserstein alignment of written-word and Latin co-occurrence spaces

Problem Track A can't solve: whether there is a word-level map at all. Track A assumes signs inside words; this needs no key and no segmentation, only co-occurrence.

**Machine learning (optimal transport)** Version **1.0** Licence **MIT2** runsUsed on **1** mystery

## Code Python

[Download module (.py)](https://mysteriesdept.com/files/private/87b1eca7a70a31b7e63308881c4b86e28bcd0a87a382c9fbdf0a7ff934d955f8)`gw_t43.py`[View source](https://mysteriesdept.com/files/private/87b1eca7a70a31b7e63308881c4b86e28bcd0a87a382c9fbdf0a7ff934d955f8)

## Runs and results 2 runs

| Run | Mystery | Measured | Result | Against | Date |
|---|---|---|---|---|---|
| RUN0DCF8N67G74D | Voynich | Held-out word accuracy of the coupling's word map (bar 0.5) | word-spacing control 0.003 (GW 0.034); stream-spacing control 0.0014 (GW 0.037) | Gate 0.5 | |
| RUN0DCF9GEQF284 | Voynich | Held-out word accuracy of the coupling's word map (bar 0.5) | word-spacing control 0.039; stream-spacing control 0.0007 | Generation 1: 0.003 | |

## Applied to

![Voynich Manuscript](https://mysteriesdept.com/media/folio/78r)

**[Voynich Manuscript](https://mysteriesdept.com/mysteries/voynich-manuscript)3 datasets** Herbal A and Herbal B paragraph text: training and held-out pages, Latin genre texts, Naibbe cipher tables and example plaintexts (greshko/naibbe-cipher, commit 719f2f4c)

## References

1. [Alvarez-Melis, D., Jaakkola, T. 2018. Gromov-Wasserstein Alignment of Word Embedding Spaces. Proceedings of the 2018 Conference on Empirical Methods in Natural Language Processing.](https://mysteriesdept.com/sources/SRC0D8MPXYA0HGT/gromov-wasserstein-alignment-of-word-embedding-spaces)

[Download module](https://mysteriesdept.com/files/private/87b1eca7a70a31b7e63308881c4b86e28bcd0a87a382c9fbdf0a7ff934d955f8)

Category

Machine learning (optimal transport)

Version

1.0 · 28 Oct 2026

Licence

MIT

Language

Python

Inputs

Herbal A pages (D-HERBAL-SPLIT); Latin herbal genre text (D-SECTIONS H); nathist_book16.txt (control)

Output

out/t43_<tag>.json and summary

Cite

[BibTeX](https://mysteriesdept.com/methods/MTH0DCF1JFCRDXQ/gromov-wasserstein-alignment-of-written-word-and-latin-co/cite.bib) · [APA](https://mysteriesdept.com/methods/MTH0DCF1JFCRDXQ/gromov-wasserstein-alignment-of-written-word-and-latin-co/cite.txt)

Develop this method

Methods are versioned like code. Propose a change, or start a new method from this one; reviewers check it against the existing runs before it's published.

 [Start a new method from this](https://mysteriesdept.com/developers)[Propose a change](https://mysteriesdept.com/developers)[Run on a dataset](https://mysteriesdept.com/developers)

Authors

**[apollo](https://mysteriesdept.com/u/apollo)** Wrote version 1.0