An Automated Approach to Syntax-based Analysis of Classical Latin

The goal of this study is to present an automated method for analyzing the style of Latin authors. Many of the common automated methods in stylistic analysis are based on lexical measures, which do not work well with Latin because of the language’s high degree of inflection and free word order. In contrast, this study focuses on analysis at a syntax level by examining two constructions, the ablative absolute and the cum clause. These constructions are often interchangeable, which suggests an author’s choice of construction is typically more stylistic than functional. We first identified these constructions in hand-annotated texts. Next we developed a method for identifying the constructions in unannotated texts, using probabilistic morphological tagging. Our methods identified constructions with enough accuracy to distinguish among different genres and different authors. In particular, we were able to determine which book of Caesar’s Commentarii de Bello Gallico was not written by Caesar. Furthermore, the usage of ablative absolutes and cum clauses observed in this study is consistent with the usage scholars have observed when analyzing these texts by hand. The proposed methods for an automatic syntax-based analysis are shown to be valuable for the study of classical literature