Machine Learning Algorithm for the Scansion of Old Saxon Poetry

Several scholars designed tools to perform the automatic scansion of poetry in many languages, but none of these tools deal with Old Saxon or Old English. This project aims to be a first attempt to create a tool for these languages. We implemented a Bidirectional Long Short-Term Memory (BiLSTM) model to perform the automatic scansion of Old Saxon and Old English poems. Since this model uses supervised learning, we manually annotated the Heliand manuscript, and we used the resulting corpus as labeled dataset to train the model. The evaluation of the performance of the algorithm reached a 97% for the accuracy and a 99% of weighted average for precision, recall and F1 Score. In addition, we tested the model with some verses from the Old Saxon Genesis and some from The Battle of Brunanburh, and we observed that the model predicted almost all Old Saxon metrical patterns correctly misclassified the majority of the Old English input verses.