Using Finite-State Machines to Automatically Scan Classical Greek Hexameter

TL;DR

This paper introduces an automatic finite-state machine-based method for analyzing Classical Greek hexameter verse, combining linguistic rules and weighted automata to improve accuracy and efficiency in scansion.

Contribution

It presents a novel finite-state automaton approach for Greek hexameter scansion, integrating deterministic automata and weighted transducers for improved analysis.

Findings

Achieves quick and linguistically sound analysis of hexameter verses

Demonstrates high annotation quality on hand-annotated data

Provides an efficient formalization of linguistic knowledge

Abstract

This paper presents a fully automatic approach to the scansion of Classical Greek hexameter verse. In particular, the paper describes an algorithm that uses deterministic finite-state automata and local linguistic rules to implement a targeted search for valid spondeus patterns and, in addition, a weighted finite-state transducer to correct and complete partial analyses and to reject invalid candidates. The paper also details the results of an empirical evaluation of the annotation quality resulting from this approach on hand-annotated data. It is shown that a finite-state approach provides quick and linguistically sound analyses of hexameter verses as well as an efficient formalisation of linguistic knowledge. The project code is available (see https://github.com/anetschka/greek_scansion).