Automated Essay Scoring in Foreign Language Students Based on Deep Contextualised Word Representations

We introduce a method for automated grading of handwritten essays written by foreign language learners of French. The handwriting recognition system allows digitising the essays for further processing and functions at a low character error rate. The transcriptions are then vectorised using embeddings from state-of-the-art pre-trained natural language processing models. On top of the extracted word-level features, a deep recurrent network was trained for grade predictions for essays, using the nine different grading criteria as target variables. Scores on these criteria were previously obtained from human expert raters for more than 6’000 student essays. We present preliminary findings on prediction accuracy and discuss possible future developments and applications of the system.