Anhang

Rengakos, Antonios; Zimmermann, Bernhard

doi:10.1007/978-3-476-05318-3_4

Cited by 1 publication

(1 citation statement)

References 0 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Moreover, some of the linguistic properties of Greek epic writing do not favour the use of machine learning, particularly in a setting where no linguistic resources are available: Ancient Greek has a rich morphology. Furthermore, it is a well-established fact (Hackstein (2011a,b); Rengakos and Zimmermann (2011)) that the texts under study do not represent a "natural", but a rather artificial language in which linguistic innovation and archaic linguistic structures co-occur side by side. Given the so far inconsistent performance of machine learning approaches on poetry scansion (see Section 3), there is reason to believe that leveraging the expert knowledge that philologists have accumulated over centuries of research may be beneficial for automatic scansion.…”

Section: Motivationmentioning

confidence: 99%

Using Finite-State Machines to Automatically Scan Classical Greek Hexameter

Schumann,

Beierle,

Blößner

2021

Preprint

View full text Add to dashboard Cite

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 online 1 .

show abstract

Section: Motivationmentioning

confidence: 99%