Learning meters of Arabic and English poems with Recurrent Neural Networks: a step forward for language understanding and synthesis

TL;DR

This paper develops RNN models to classify Arabic and English poem meters directly from raw text, achieving high accuracy and providing publicly available datasets for future research in language understanding and synthesis.

Contribution

It introduces the first machine learning approach using RNNs for poem meter classification and releases the largest publicly available dataset for this task.

Findings

Achieved 96.38% accuracy on Arabic poem meters

Achieved 82.31% accuracy on English poem meters

Provided publicly available, structured datasets for future research

Abstract

Recognizing a piece of writing as a poem or prose is usually easy for the majority of people; however, only specialists can determine which meter a poem belongs to. In this paper, we build Recurrent Neural Network (RNN) models that can classify poems according to their meters from plain text. The input text is encoded at the character level and directly fed to the models without feature handcrafting. This is a step forward for machine understanding and synthesis of languages in general, and Arabic language in particular. Among the 16 poem meters of Arabic and the 4 meters of English the networks were able to correctly classify poem with an overall accuracy of 96.38\% and 82.31\% respectively. The poem datasets used to conduct this research were massive, over 1.5 million of verses, and were crawled from different nontechnical sources, almost Arabic and English literature sites, and in different heterogeneous and unstructured formats. These datasets are now made publicly available in clean, structured, and documented format for other future research. To the best of the authors' knowledge, this research is the first to address classifying poem meters in a machine learning approach, in general, and in RNN featureless based approach, in particular. In addition, the dataset is the first publicly available dataset ready for the purpose of future computational research.