Transformer-based Hebrew NLP models for Short Answer Scoring in Biology
Abigail Gurin Schleifer, Beata Beigman Klebanov, Moriah Ariely, Giora Alexandron · 2023
Pre-trained large language models (PLMs) are adaptable to a wide range of downstream tasks by fine-tuning their rich contextual embeddings to the task, often without requiring much taskspecific data.In this paper, we explore the use of a recently developed Hebrew PLM -aleph-BERT -for automated short answer grading of high school biology items.We show that the alephBERT-based system outperforms a strong CNN-based baseline, and that it generalizes unexpectedly well in a zero-shot paradigm to items on an unseen topic that address the same underlying biological concepts, opening up the possibility of automatically assessing new items without item-specific fine-tuning.