# Gianluca Vico 2023: Larth: Dataset and Machine Translation for Etruscan

> Gianluca Vico, Gerasimos Spanakis, 2023. 6 records on Mysteries Department cite it. Proceedings of the Ancient Language Processing Workshop (ALP 2023…

Source: https://mysteriesdept.com/sources/SRC0DEDNJJ091N0/larth-dataset-and-machine-translation-for-etruscan  
Publisher: Mysteries Department  
Licence: CC BY 4.0 (credit Mysteries Department and link the page)  

---

[Sources](https://mysteriesdept.com/sources)[Etruscan: the readable language that cannot be fully translated](https://mysteriesdept.com/mysteries/etruscan-language)Gianluca Vico 2023

**0**

# Larth: Dataset and Machine Translation for Etruscan

Gianluca Vico, Gerasimos Spanakis, 2023.

**Etruscan: the readable language that cannot be fully translated** Paper-conferenceCopy of **[Liber Linteus Zagrabiensis (the Zagreb linen book, ET LL)](https://mysteriesdept.com/mysteries/etruscan-language/artifacts/ART0DEDW9VYCNGC/liber-linteus-zagrabiensis-the-zagreb-linen-book-et-ll)** 0

## What it's used for here

Proceedings of the Ancient Language Processing Workshop (ALP 2023, RANLP), pp. 39-48; also arXiv:2310.05688. The first public Etruscan NLP dataset: 7,139 inscriptions from ETP and CIE I, 2,891 with English translations; a small transformer reaches BLEU 10.1 on Etruscan-to-English. Code and data CC BY 4.0 on GitHub.

## Cited by on this site 6 records

[Liber Linteus Zagrabiensis: transcription excerpts (ET LL in the Larth dataset)](https://mysteriesdept.com/mysteries/etruscan-language/copies/CPY0DEDX070CWMQ/liber-linteus-zagrabiensis-transcription-excerpts-et-ll-in)

CPY

[Larth Etruscan corpus (Etruscan.csv): 7,139 inscriptions, 2,891 with English translation](https://mysteriesdept.com/datasets/DAT0DEDXR3X5TB5/larth-etruscan-corpus-etruscan-csv-7-139-inscriptions-2-891)

Dataset

DAT

[The best Etruscan-to-English model trained on 2,891 translated inscriptions reached BLEU 10.1.](https://mysteriesdept.com/mysteries/etruscan-language/evidence/EVD0DEECND3S6S0/the-best-etruscan-to-english-model-trained-on-2-891)

Evidence

EVD

[Vico and Spanakis release the Larth dataset and the first Etruscan machine-translation benchmark](https://mysteriesdept.com/mysteries/etruscan-language/events/EVT0DEDVF7RTYQW/vico-and-spanakis-release-the-larth-dataset-and-the-first)

EVT

[Etruscan: the readable language that cannot be fully translated](https://mysteriesdept.com/mysteries/etruscan-language)

The mystery article

MYS

[How far can the combinatory method and computational analysis extend the roughly 250 securely understood Etruscan words?](https://mysteriesdept.com/mysteries/etruscan-language/questions/QST0DEDYMXF5X5P/how-far-can-the-combinatory-method-and-computational)

Question

QST

## Cite it

```
Gianluca Vico, & Gerasimos Spanakis (2023). Larth: Dataset and Machine Translation for Etruscan. https://aclanthology.org/2023.alp-1.5/
```

[Find it at aclanthology.org](https://aclanthology.org/2023.alp-1.5/)

Key

**SRC** 0DEDNJJ091N0

Kind

Paper-conference

Rights

The publisher's

Kept

31 Oct 2026, for editors

Added by

[apollo](https://mysteriesdept.com/u/apollo)

The record

Bibliographic records are CC0. Take this one as CSL-JSON, BibTeX or RIS.

[CSL-JSON](https://mysteriesdept.com/sources/SRC0DEDNJJ091N0/larth-dataset-and-machine-translation-for-etruscan/csl.json)