Unsupervised rhyme recognition across multiple languages: training data size, human agreement, and linguistic differences
Digital Scholarship in the Humanities · 25.07.2026
DOI: 10.1093/llc/fqag098 ↗Kurz gefasst
Fachartikel in der Zeitschrift Digital Scholarship in the Humanities, online erschienen am 25.07.2026. Verfasst von Petr Plecháč und 9 weiteren Autor:innen. Die Arbeit nennt 12 Literaturangaben. Gefördert von: Czech Science Foundation.
Abstract (Originalsprache)
Rhyme is deceptively intuitive: what is or is not a rhyme is constructed historically, scholars struggle with rhyme classification, and people disagree on whether two words are rhymed or not. This complicates automated rhymed recognition and evaluation, especially in cross-language research contexts. This article investigates how much training data are needed for reliable unsupervised rhyme recognition using RhymeTagger, a language-independent tool that identifies rhymes based on repeating patterns in poetry corpora. We evaluate its performance across seven languages (Czech, German, English, French, Italian, Russian, and Slovene), examining how training size and language differences affect accuracy. To set a realistic performance benchmark, we assess inter-annotator agreement on a manually annotated subset of poems and analyze factors contributing to disagreement in expert annotations: phonetic similarity between rhyming words and their distance from each other in a poem. We also compare RhymeTagger to three large language models (LLMs) using a one-shot learning strategy. Our findings show that, once provided with sufficient training data, RhymeTagger consistently outperforms human agreement, while LLMs lacking phonetic representation significantly struggle with the task.
Förderung
- Czech Science Foundation
Zitieren
APA
Plecháč, P., Šeļa, A., Nagy, B., Cinková, S., Sisto, M. D., Nugues, L., Kočnik, N., Martynenko, A., Giovannini, L., & Kolár, R. (2026). Unsupervised rhyme recognition across multiple languages: training data size, human agreement, and linguistic differences. Digital Scholarship in the Humanities. https://doi.org/10.1093/llc/fqag098
Vancouver
Plecháč P, Šeļa A, Nagy B, Cinková S, Sisto MD, Nugues L, et al. Unsupervised rhyme recognition across multiple languages: training data size, human agreement, and linguistic differences. Digital Scholarship in the Humanities. 2026. doi:10.1093/llc/fqag098
BibTeX
@article{Plech2026,
author = {Plecháč, Petr and Šeļa, Artjoms and Nagy, Ben and Cinková, Silvie and Sisto, Mirella De and Nugues, Lara and Kočnik, Neža and Martynenko, Antonina and Giovannini, Luca and Kolár, Robert},
title = {Unsupervised rhyme recognition across multiple languages: training data size, human agreement, and linguistic differences},
journal = {Digital Scholarship in the Humanities},
year = {2026},
doi = {10.1093/llc/fqag098}
}
EUVIMED