BERT in Plutarch's Shadows

TL;DR

This paper introduces a BERT language model tailored for Ancient Greek, which uncovers new statistical insights into Pseudo-Plutarch texts, aiding authorship attribution and historical analysis.

Contribution

It presents a novel BERT-based approach for Ancient Greek that reveals previously unknown linguistic patterns relevant to authorship and historical context.

Findings

Pseudo-Plutarch texts show similarities with Alexandrian authors

The model uncovers new statistical properties of ancient texts

Insights support hypotheses about authorship and historical connections

Abstract

The extensive surviving corpus of the ancient scholar Plutarch of Chaeronea (ca. 45-120 CE) also contains several texts which, according to current scholarly opinion, did not originate with him and are therefore attributed to an anonymous author Pseudo-Plutarch. These include, in particular, the work Placita Philosophorum (Quotations and Opinions of the Ancient Philosophers), which is extremely important for the history of ancient philosophy. Little is known about the identity of that anonymous author and its relation to other authors from the same period. This paper presents a BERT language model for Ancient Greek. The model discovers previously unknown statistical properties relevant to these literary, philosophical, and historical problems and can shed new light on this authorship question. In particular, the Placita Philosophorum, together with one of the other Pseudo-Plutarch texts, shows similarities with the texts written by authors from an Alexandrian context (2nd/3rd century CE).