Automated Metric Analysis of Spanish Poetry: Two Complementary Approaches

The automatic metric analysis (commonly referred to as scansion ) of Spanish poetry is not a trivial problem since it combines the nuances language, different poetic traditions related melodic patterns, and personal stylistic preferences intentions author. In this paper, we explore two alternative algorithmic approaches tailored applications scenarios. first approach, Rantanplan, rule-based method that consists four Natural Language Processing modules work together perform other analysis: Part Speech tagging, syllabification, stress assignment, metrical adjustment. second Jumper, explores possibility performing without with twofold purpose: minimize errors propagated in parts linguistic processing pipeline (including syllabification step), improve efficiency process. Both systems outperform state art provide either more informative solution (suitable, for instance, teaching purposes) or efficient (when correct all knowledge required, scholar philological studies). combined use both turns out practical tool clean-up manual annotation corpora.