Logo
ScienceStack
Table of Contents
Fetching ...
Sign In

Metronome: tracing variation in poetic meters via local sequence alignment

Ben Nagy, Artjoms Šeļa, Mirella De Sisto, Petr Plecháč

TL;DR

Metronome tackles the challenge of tracing metrical relationships across languages and historical periods by converting poems into sequences over a minimal four-letter prosodic alphabet and applying local sequence alignment. The approach, grounded in Smith-Waterman alignment, yields a distance metric that supports clustering and cross-linguistic comparison without requiring predefined evolutionary models. Through three cross-language case studies and a cross-linguistic meter evaluation, the paper demonstrates the method's ability to reveal structural similarities and divergences in metrical organization, while releasing an open-source Python package for reproducible analysis. This work provides a scalable, theory-leaning tool for historical and comparative versification research, enabling distant reading of meter across corpora and traditions.

Abstract

All poetic forms come from somewhere. Prosodic templates can be copied for generations, altered by individuals, imported from foreign traditions, or fundamentally changed under the pressures of language evolution. Yet these relationships are notoriously difficult to trace across languages and times. This paper introduces an unsupervised method for detecting structural similarities in poems using local sequence alignment. The method relies on encoding poetic texts as strings of prosodic features using a four-letter alphabet; these sequences are then aligned to derive a distance measure based on weighted symbol (mis)matches. Local alignment allows poems to be clustered according to emergent properties of their underlying prosodic patterns. We evaluate method performance on a meter recognition tasks against strong baselines and show its potential for cross-lingual and historical research using three short case studies: 1) mutations in quantitative meter in classical Latin, 2) European diffusion of the Renaissance hendecasyllable, and 3) comparative alignment of modern meters in 18--19th century Czech, German and Russian. We release an implementation of the algorithm as a Python package with an open license.

Metronome: tracing variation in poetic meters via local sequence alignment

TL;DR

Metronome tackles the challenge of tracing metrical relationships across languages and historical periods by converting poems into sequences over a minimal four-letter prosodic alphabet and applying local sequence alignment. The approach, grounded in Smith-Waterman alignment, yields a distance metric that supports clustering and cross-linguistic comparison without requiring predefined evolutionary models. Through three cross-language case studies and a cross-linguistic meter evaluation, the paper demonstrates the method's ability to reveal structural similarities and divergences in metrical organization, while releasing an open-source Python package for reproducible analysis. This work provides a scalable, theory-leaning tool for historical and comparative versification research, enabling distant reading of meter across corpora and traditions.

Abstract

All poetic forms come from somewhere. Prosodic templates can be copied for generations, altered by individuals, imported from foreign traditions, or fundamentally changed under the pressures of language evolution. Yet these relationships are notoriously difficult to trace across languages and times. This paper introduces an unsupervised method for detecting structural similarities in poems using local sequence alignment. The method relies on encoding poetic texts as strings of prosodic features using a four-letter alphabet; these sequences are then aligned to derive a distance measure based on weighted symbol (mis)matches. Local alignment allows poems to be clustered according to emergent properties of their underlying prosodic patterns. We evaluate method performance on a meter recognition tasks against strong baselines and show its potential for cross-lingual and historical research using three short case studies: 1) mutations in quantitative meter in classical Latin, 2) European diffusion of the Renaissance hendecasyllable, and 3) comparative alignment of modern meters in 18--19th century Czech, German and Russian. We release an implementation of the algorithm as a Python package with an open license.
Paper Structure (9 sections, 6 figures)

This paper contains 9 sections, 6 figures.

Table of Contents

  1. Introduction
  2. Method
  3. Evaluation
  4. Data and sampling
  5. Classification Methods
  6. Results
  7. Showcases
  8. Discussion
  9. Availability of Data and Code

Figures (6)

  • Figure 1: Classification performance of Metronome vs SVM and two baseline alignment algorithms. Smoothed distribution of accuracy results over 50 random subsamples, with median scores.
  • Figure 2: Cladogram of a selection of poems by Catullus. Carmen 55, while still composed in hendecasyllables, is visibly different to the rest of that clade.
  • Figure 3: A visual comparison of the metronome strings (formatted to add line breaks) for the beginning of Carmina 55 (variant with collapsed choriamb) and 41 (standard hendecasyllable).
  • Figure 4: A metronome-based cladogram of various samples of Renaissance meter. The inset number is the entropy-based variability from the regular metrical form (see sela_measuring_2022). Shakespeare is the most regular, de La Torre the least.
  • Figure 5: UMAP cluster of 3222 poems in Czech, German, and Russian from the PoeTree corpus, in the six most common European meters. Metronome distance is used as the clustering metric.
  • ...and 1 more figures