Skip to main content

ETHNOS_APP

Home • Search • Journals • List 0

LibEscansión

A Recursive Precedence Approach to Metrical Scansion

Bibliographic Data

ID21835810
AuthorsFernando Sanz-Lázaro (0000-0002-8815-6741, corresponding author)
Year2024
Volume18
Issue3
Publication date2024-07-19
Open AccessYes
TypeARTICLE
VenueDigital humanities quarterly (JOURNAL)
Journal identifiersISSN: 1938-4122 • E-ISSN: 1938-4122
PublisherThe Association for Computers and the Humanities (PUBLISHER)
DOI10.63744/fjf9b44n9bk2
OpenAlexW7139925091
LanguageES

In recent years, there has been impressive progress in the automatic analysis of Spanish verse. However, despite the excellent results of previous attempts, there is still room for improvement, as this article shows. It presents libEscansión, a new automatic scansion tool that, although initially designed for analysing the verses of plays, outperforms all its predecessors in the scansion of fixed-meter poetry. The library uses two novel approaches to achieve this result: linguistically, it uses Castilian syllabification instead of the more diphthong-prone American syllabic division. It uses a dedicated module that can also be run independently. Methodologically, the library resolves metrical ambiguities using a perceptibility-based recursive prioritisation system. The combination of both allows libEscansión to perform a scansion 0.78% more accurately than the best of its peers against a gold standard corpus, reaching an accuracy of 97.01% (99.50% discarding non-erroneous disagreements)

Automation · Syllabic verse · Syllabification · Artificial Intelligence in Games · Authorship Attribution and Profiling · Digital Humanities and Scholarship

Highly citedNo

Tools

Open DOIOpen Access
Ethnos_APP • Open Source Project • MIT License • Frontend v2.0.0 • Privacy and Cookies • API Documentation: api.ethnos.app/docs • API Source Code: GitHub • DOI: 10.5281/zenodo.17049435 • Frontend Source Code: GitHub • DOI: 10.5281/zenodo.17050053 • cruz.rio.br • Expectantes Misericordiae