DeepEva: A deep neural network architecture for assessing sentence complexity in Italian and English languages

Automatic Text Complexity Evaluation (ATE) is a research field that aims at creating new methodologies to make autonomous the process of text complexity evaluation, study text-linguistic features (e.g., lexical, syntactical, morphological) measure grade comprehensibility text. ATE can affect positively several different contexts such as Finance, Health, and Education. Moreover, it support on Simplification (ATS), area deals with methods for transforming by changing its lexicon structure meet specific reader needs. In this paper, we illustrate an approach named DeepEva, Deep Learning based system capable classifying both Italian English sentences basis their complexity. The exploits Treetagger annotation tool, two Long Short Term Memory (LSTM) neural unit layers, fully connected one. last layer outputs probability sentence belonging easy or complex class. experimental results show effectiveness languages, compared baselines Support Vector Machine, Gradient Boosting, Random Forest.