A Simple Post-Processing Technique for Improving Readability Assessment of Texts using Word Mover's Distance
This work addresses readability assessment for texts in multiple languages, but it is incremental as it builds on existing methods with a simple post-processing step.
The paper tackled the problem of automatic readability assessment by incorporating Word Mover's Distance as a post-processing technique to ground difficulty levels, resulting in improved performance over previous models on multilingual datasets in Filipino, German, and English.
Assessing the proper difficulty levels of reading materials or texts in general is the first step towards effective comprehension and learning. In this study, we improve the conventional methodology of automatic readability assessment by incorporating the Word Mover's Distance (WMD) of ranked texts as an additional post-processing technique to further ground the difficulty level given by a model. Results of our experiments on three multilingual datasets in Filipino, German, and English show that the post-processing technique outperforms previous vanilla and ranking-based models using SVM.