Metrical Tagging in the Wild: Building and Annotating Poetry Corpora with Rhythmic Features

TL;DR

This paper develops and annotates large English and German poetry corpora with prosodic features, training neural models to analyze rhythmic and metrical patterns in poetry at scale.

Contribution

It introduces new multilingual poetry corpora with prosodic annotations and demonstrates neural models that outperform baselines in metrical tagging tasks.

Findings

BiLSTM-CRF models outperform baselines and BERT-based approaches.

Joint prediction of poetic features improves model performance.

Caesuras are closely linked to syntax and influence line measures.

Abstract

A prerequisite for the computational study of literature is the availability of properly digitized texts, ideally with reliable meta-data and ground-truth annotation. Poetry corpora do exist for a number of languages, but larger collections lack consistency and are encoded in various standards, while annotated corpora are typically constrained to a particular genre and/or were designed for the analysis of certain linguistic features (like rhyme). In this work, we provide large poetry corpora for English and German, and annotate prosodic features in smaller corpora to train corpus driven neural models that enable robust large scale analysis. We show that BiLSTM-CRF models with syllable embeddings outperform a CRF baseline and different BERT-based approaches. In a multi-task setup, particular beneficial task relations illustrate the inter-dependence of poetic features. A model learns foot boundaries better when jointly predicting syllable stress, aesthetic emotions and verse measures benefit from each other, and we find that caesuras are quite dependent on syntax and also integral to shaping the overall measure of the line.