Automatic Metrical Scansion of Galician Poetry: First Results

2026-04-12 · Source: Paper Index on ACL Anthology · Field: Technology & Digital — Artificial Intelligence & Machine Learning, Data Science & Analytics, Computational Literary Studies · Depth: Expert, quick

Summary

A new public, user-friendly system has been developed for the automatic metrical scansion of Galician poetry. This system is an adaptation of a successful mixed-meter Spanish scansion library, with its resources modified for Galician and an added preprocessing module. It demonstrates an 88% per-line accuracy in exact stress-pattern matching on previously unseen data. The system offers practical applications, including facilitating the creation of a large annotated corpus for training future scansion systems, engaging a non-specialist public through its web interface, and supporting computational literary studies by enabling the annotation of extensive poetry volumes and the analysis of metrical trends.

Key takeaway

For computational linguists or literary scholars working with Galician texts, this new scansion system offers a valuable tool for automating metrical analysis. You can leverage its 88% accuracy to rapidly annotate large volumes of poetry, significantly accelerating corpus creation and enabling deeper studies into metrical trends. Consider integrating this system to enhance research efficiency and broaden public engagement with Galician poetry.

Key insights

A new system provides automatic metrical scansion for Galician poetry with 88% accuracy.

Principles

• Adapt existing resources for new languages.
• Preprocessing improves system performance.

Method

The system adapts a Spanish scansion library's resources to Galician and incorporates a preprocessing module to achieve automatic metrical scansion.

In practice

• Create large annotated corpora.
• Engage non-specialist audiences.
• Study metrical trends in literature.

Topics

• Galician Poetry Scansion
• Metrical Scansion System
• Computational Literary Studies
• Stress Pattern Analysis
• Natural Language Processing

Best for: AI Scientist, NLP Engineer, Research Scientist, General Interest

Related on AIssential

• Improving Machine Translation of Idioms: A Spanish–Galician Parallel Dataset and Synthetic Augmentation Approach — Synthetic data augmentation using LLMs significantly improves idiom translation in neural machine translation.
• A elaboração de uma edição digital d’Os Lusíadas — Integrating philology, Digital Humanities, and NLP creates comprehensive digital critical editions.
• BullingerDB: A Dataset for Handwritten Text Recognition and Writer Retrieval — BullingerDB is a large, multilingual dataset for historical HTR and writer retrieval, introducing temporal metrics and highlighting challenges from long-term stylistic variation.
• How I built a rhyme quality scoring algorithm for the French language — Quantifying rhyme quality requires phonemic analysis and articulatory proximity matrices, not just letter matching.
• Not Search, But Scan: Benchmarking MLLMs on Scan-Oriented Academic Paper Reasoning — Scan-oriented reasoning benchmarks reveal MLLM deficiencies in full-document understanding and cross-checking.
• PorTEXTO: A European Portuguese Benchmark for Visual Text Extraction — Specialized multilingual data significantly improves European Portuguese OCR performance over model size or resolution.

Open in AIssential →

Editorial summary, takeaway, and curation by AIssential. Original article published by Paper Index on ACL Anthology.