PILA: A Historical-Linguistic Dataset of Proto-Italic and Latin

TL;DR

PILA introduces a historical-phonological dataset of Proto-Italic to Latin, linking Proto-Italic etyma to Latin reflexes across approximately 3,000 pairs. Built in a CLDF framework, it provides full reconstructions, inflected forms, and rich morphological tags to support phonological and morphological analyses of Italic sound change. The authors demonstrate PILA’s value with Transformer-based reflex prediction and etymon reconstruction baselines and show that PILA can enhance and align with other historical-linguistic datasets through a detailed compatibility study. This resource enables more rigorous modeling of historical sound changes and offers a pathway to integrating broader Italic data and potential automatically induced sound-laws.

Abstract

Computational historical linguistics seeks to systematically understand processes of sound change, including during periods at which little to no formal recording of language is attested. At the same time, few computational resources exist which deeply explore phonological and morphological connections between proto-languages and their descendants. This is particularly true for the family of Italic languages. To assist historical linguists in the study of Italic sound change, we introduce the Proto-Italic to Latin (PILA) dataset, which consists of roughly 3,000 pairs of forms from Proto-Italic and Latin. We provide a detailed description of how our dataset was created and organized. Then, we exhibit PILA's value in two ways. First, we present baseline results for PILA on a pair of traditional computational historical linguistics tasks. Second, we demonstrate PILA's capability for enhancing other historical-linguistic datasets through a dataset compatibility study.

Figures (1)

• Figure 1: Partial family tree of Italic and Latin. Dashed lines indicate the omission of some intermediate families and branching structures from the tree. The two points represent the time periods covered by our dataset.