Statistical Measures for Readability Assessment

Neural models and deep learning techniques have predominantly been used in many tasks of natural language processing (NLP), including automatic readability assessment (ARA). They apply deep transfer learning and enjoy high accuracy. However, most of the models still cannot leverage long dependence such as inter-sentential topic-level or document-level information because of their structure and computational cost. Moreover, neural models usually have low interpretability. In this paper, we propose a generalization of passage-level, corpus-level, document-level and topic-level features. In experiments, we show the effectiveness of ``Statistical Lexical Spread (SLS)'' features when combined IDF and TF-IDF, which adds a topological perspective to readability to complement the typological approaches (used in the readability formulas). Interestingly, simply adding these features in BERT models outperformed state-of-the-art systems trained on a large number of hand-crafted features derived from heavy linguistic processing. In analysis, we show that SLS is also easy-to-interpret because SLS computes lexical features, which appear explicitly in texts, compared to parameters in neural models.