Etruscan Typology
Computational tools for the typological classification of unprovenanced inscriptions, the restoration of fragmentary text, and morphological analysis.
How it Works
Etruscan is a corpus language whose vocabulary and grammar are only partially understood; epigraphic interpretation relies on rigid formulaic patterns shared across inscriptions.
This classifier is trained on 282 silver-labelled inscriptions (the v2 training pool) and evaluated on 143 candidate-gold rows from a 400-row stratified test split (v2.0.2, 3-rater jury). It predicts one of seven epigraphic categories — funerary, ownership, dedicatory, votive, legal, boundary, commercial — by character n-gram + Naive Bayes / neural patterns. The head-2 classes (funerary, ownership) are well modelled; the rare tail is data-starved.
Developer API
The model executes completely within the browser using WebAssembly, ensuring immediate analysis without server roundtrips.
POST /api/v1/inference/classify
{
"model": "transformer-v2",
"text": "mi larzaia"
}