A Baseline Readability Model for Cebuano

TL;DR

This paper introduces the first baseline readability model for Cebuano, utilizing surface features, syllable patterns, and neural embeddings, achieving around 87% accuracy with a Random Forest classifier, and promotes further research in Philippine languages.

Contribution

It presents the initial readability assessment model for Cebuano, combining traditional features and neural embeddings, and demonstrates crosslingual applicability with open-sourced resources.

Findings

Achieved approximately 87% performance with handcrafted features and Random Forest.

Surface features and syllable patterns are effective for Cebuano readability.

Open-sourced code and data to foster further research.

Abstract

In this study, we developed the first baseline readability model for the Cebuano language. Cebuano is the second most-used native language in the Philippines with about 27.5 million speakers. As the baseline, we extracted traditional or surface-based features, syllable patterns based from Cebuano's documented orthography, and neural embeddings from the multilingual BERT model. Results show that the use of the first two handcrafted linguistic features obtained the best performance trained on an optimized Random Forest model with approximately 87% across all metrics. The feature sets and algorithm used also is similar to previous results in readability assessment for the Filipino language showing potential of crosslingual application. To encourage more work for readability assessment in Philippine languages such as Cebuano, we open-sourced both code and data.