Larth: Dataset and Machine Translation for Etruscan
This work addresses the problem of scarce resources for Etruscan, an ancient language, enabling future research on it and similar low-resource languages, though it is incremental as it applies existing methods to new data.
The authors tackled the lack of publicly available Etruscan corpora for natural language processing by creating a dataset of 2891 translated examples from Etruscan to English, and they achieved a BLEU score of 10.1 using a small transformer model for machine translation.
Etruscan is an ancient language spoken in Italy from the 7th century BC to the 1st century AD. There are no native speakers of the language at the present day, and its resources are scarce, as there exist only around 12,000 known inscriptions. To the best of our knowledge, there are no publicly available Etruscan corpora for natural language processing. Therefore, we propose a dataset for machine translation from Etruscan to English, which contains 2891 translated examples from existing academic sources. Some examples are extracted manually, while others are acquired in an automatic way. Along with the dataset, we benchmark different machine translation models observing that it is possible to achieve a BLEU score of 10.1 with a small transformer model. Releasing the dataset can help enable future research on this language, similar languages or other languages with scarce resources.