This is a repository of the paper titled "Arabic Poetry Metric Classification Using Bidirectional Gated Recurrent Neural Networks" - link.

Poetry is an important component of any language. Much of a nation's history and culture are documented in poems. A poem has a rhythm flow which is quite different as compared to a prose. Each language has its own set of rhythmical structures for its poems, called meters. Identifying the meters of Arabic poems is a lengthy and complicated process. To classify a poem's meter, the text of the poem should be encoded in a special Arudi form which needs complex rule-based transformations before another set of rules can be used to finally classify the meters. This paper introduces a novel method for classifying poem meters of Arabic poems using RNN-based deep learning. It bypasses the need to transform the poem to the Arudi form as well as the need to explicitly encode the complex rules that are usually followed to determine the meter. The presented method was evaluated on a large dataset collected specifically for this purpose. We are able to classify the poem meters with an accuracy of 94.32% on an independent test set.

We use Bidirectional GRU layers for training a character model for classifying 'baits' into one of 14 classes. Note that we discard the last two meters because we don't have enough data for them.

Check the notebook AraMeter.ipynb for retraining the model. You can run it directly in google colab.

Check full_verse.h5 for a the full trained model. You can load it directly using TensorFlow with the following command model = tensorflow.keras.models.load_model('full_verse.h5')

We acheive the following results compared to literature

The dataset is in the file baits.zip it is splitted into two files for training train.txt and testing test.txt and the labels of the meters are saved in the file labels.txt. The dataset was scrapped from Aldiwan which is an encyclopedia of Arabic poetry where each poem is labeled by corrosponding poet, meter, era, etc.

A "smaller" model can be tested on the browser using the following demo.

MIT

@article{al2020meter,
  title={Meter Classification of Arabic Poems Using Deep Bidirectional Recurrent Neural Networks},
  author={Al-shaibani, Maged S and Alyafeai, Zaid and Ahmad, Irfan},
  journal={Pattern Recognition Letters},
  year={2020},
  publisher={Elsevier}
}