Graecia capta ferum victorem cepit. Detecting Latin Allusions to Ancient Greek Literature

TL;DR

This paper introduces SPhilBERTa, a trilingual model designed to detect Latin allusions to Greek literature by cross-lingual semantic analysis, enhancing classical philology research through automated intertextual reference identification.

Contribution

We develop SPhilBERTa, the first trilingual Sentence-RoBERTa model for Classical Philology, enabling cross-lingual detection of intertextual references among Latin, Greek, and English texts.

Findings

SPhilBERTa effectively identifies intertextual parallels across languages.

Generated training data by translating English into Greek improves model performance.

Demonstrated practical application through a case study.

Abstract

Intertextual allusions hold a pivotal role in Classical Philology, with Latin authors frequently referencing Ancient Greek texts. Until now, the automatic identification of these intertextual references has been constrained to monolingual approaches, seeking parallels solely within Latin or Greek texts. In this study, we introduce SPhilBERTa, a trilingual Sentence-RoBERTa model tailored for Classical Philology, which excels at cross-lingual semantic comprehension and identification of identical sentences across Ancient Greek, Latin, and English. We generate new training data by automatically translating English texts into Ancient Greek. Further, we present a case study, demonstrating SPhilBERTa's capability to facilitate automated detection of intertextual parallels. Our models and resources are available at https://github.com/Heidelberg-NLP/ancient-language-models.