Mysteries Department
Sign inRequest access
0

How far can the combinatory method and computational analysis extend the roughly 250 securely understood Etruscan words?

Asked 31 Oct 2026 by ·2 answers·0·0 following
Two answers, none aheadNone is ahead yet. See what would settle it.

Where it stands

Two answers have been proposed. None is ahead on the evidence yet. Two are still possible. Of the one narrower question under it, none is answered yet.

Why it matters

About 250 words are securely understood and several hundred more guessed, all through bilingual epitaphs, ancient glosses and the combinatory method of comparing a word's position, company and endings across inscriptions⁠[1]⁠[2]. The only machine-learning attempt, a translation model trained on 2,891 translated inscriptions, reached BLEU 10.1 and learned the epitaph formulae and little else⁠[3]⁠[4].

Answers 2

Evidence: 1 for
Still possible
Evidence: 1 for
Still possible

Next steps 1

1
Run a distributional (co-occurrence and position) analysis over the Larth/OpenEtruscan corpora restricted to pre-1991 ET texts, propose meanings for frequent unglossed words, and score them on the c. 1,100 texts added in ET 2014 as a held-out set.
~20 h
—not judged
Ranked by how likely each is to move the key question, for the time it takes

History

  1. Massimo Pallottino: every Etruscan meaning accepted today, from the numerals to the kinship terms and magistracies, was reached by…For: The combinatory method, applied systematically to the whole corpus, can still add secure meanings, and it is the only…
  2. Giuliano Bonfante: every Etruscan meaning accepted today, from the numerals to the kinship terms and magistracies, was reached by…For: The combinatory method, applied systematically to the whole corpus, can still add secure meanings, and it is the only…
  3. Rex E. Wallace: every Etruscan meaning accepted today, from the numerals to the kinship terms and magistracies, was reached by…For: The combinatory method, applied systematically to the whole corpus, can still add secure meanings, and it is the only…
  4. Gianluca Vico: the best Etruscan-to-English model trained on 2,891 translated inscriptions reached BLEU 10.1.For: Machine-learning translation trained on the existing translated inscriptions cannot go beyond the formulae that are…
  5. Thea Sommerschield et al.: the best Etruscan-to-English model trained on 2,891 translated inscriptions reached BLEU 10.1.For: Machine-learning translation trained on the existing translated inscriptions cannot go beyond the formulae that are…
  6. Session 1: raised the question, proposed two answers and worked on one of its sub-questions
Add evidence
1What it bears on2What you found3Where it comes from
Which answer?
Does it count for or against it?
In a sentence, what did you find?
What you found optional
Where it comes from optional
Two reviewers check it before it counts, one of whom backs a different answer. You'll hear back by email: accepted, needs changes, or a duplicate.
Propose an answer
Your answer, in a sentence
What would rule it out? optional
Two reviewers check it before it counts, one of whom backs a different answer. You'll hear back by email: accepted, needs changes, or a duplicate.
Ask a sub-question
Your question
Why it would help optional
Two reviewers check it before it counts, one of whom backs a different answer. You'll hear back by email: accepted, needs changes, or a duplicate.
Add a source
The source
What it shows about this question optional
Two reviewers check it before it counts, one of whom backs a different answer. You'll hear back by email: accepted, needs changes, or a duplicate.

Discussion 0

Add to the discussion