Lexical Complexity Prediction: An Overview

The occurrence of unknown words in texts significantly hinders reading comprehension. To improve accessibility for specific target populations, computational modeling has been applied to identify complex and substitute them simpler alternatives. In this article, we present an overview approaches lexical complexity prediction focusing on the work carried out English data. We survey relevant problem which include traditional machine learning classifiers (e.g., SVMs, logistic regression) deep neural networks as well a variety features, such those inspired by literature psycholinguistics word frequency, length, many others. Furthermore, introduce readers past competitions available datasets created topic. Finally, brief sections applications prediction, readability text simplification, together with related studies languages other than English.