Workshop 'Data-driven Approaches to Ancient Languages'

Premodern or historically attested languages are invaluable resources of both the study of diachronic linguistics and their contemporary culture. Although these languages might be from various language families or have a different script, researchers face common challenges, among which illegible or lost text (parts), inexistent gold standards and, very important these days, scarcity of data.

Luckily, more and more texts become available, but the language of those texts might be so different from their modern pendant — should that modern pendant exist — that it considerably impacts the performance of existing tools.

This workshop aims to provide a platform to a broad field of researchers engaged in digital approaches to pre-modern languages.