Work

Transformer-based Hebrew NLP models for Short Answer Scoring in Biology

Year: 2023

Type: conference-paper

Abstract: 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.

Source: Workshop on Innovative Use of NLP for Building Educational Applications

DOI: 10.18653/v1/2023.bea-1.46

Authors: Abigail Gurin Schleifer, Beata Beigman Klebanov, Moriah Ariely, Giora Alexandron

Institutions: Weizmann Institute of Science, Educational Testing Service

Language: English

Topic: Topic Modeling

Subfield: Artificial Intelligence

Field: Computer Science

Domain: Physical Sciences

SDG: Quality education

Open Access status: hybrid

Funders: Council for Higher Education, Division of Chemistry