RS_GV at SemEval-2021 Task 1: Sense Relative Lexical Complexity Prediction

Abstract

We present the technical report of the system called RS GV at SemEval-2021 Task 1 on complexity prediction of English words. RS GV is a neural network using hand-crafted linguistic features in combination with character and word embeddings to predict the target words' complexity. For the generation of the handcrafted features, we set the target words in relation to their senses. RS GV predicts the complexity well of biomedical terms but it has problems with the complexity prediction of very complex and very simple target words.