Indonesian automated short-answer grading using transformers-based semantic similarity

Abstract

Automatic short answer grading (ASAG) systems offer a promising solution for improving the efficiency of reading literacy assessments. While promising, current Indonesian artificial intelligence (AI) grading systems still have room for improvement, especially when dealing with different domains. This study explores the effectiveness of large language models, specifically bidirectional encoder representations from transformers (BERT) variants, in conjunction with traditional hand-engineered features, to improve ASAG accuracy. We conducted experiments using various BERT models, hand-engineered features, text pre-processing techniques, and dimensionality reduction. Our findings show that BERT models consistently outperform traditional methods like term frequency-inverse document frequency (TF-IDF). IndoBERTLite-Base-P2 achieved the highest quadratic weighted kappa (QWK) score among the BERT variants. Integrating handengineered features with BERT resulted in a substantial enhancement of the QWK score. Utilizing comprehensive text pre-processing is a critical factor in achieving optimal performance. In addition, dimensionality reduction should be carefully used because it potentially removes semantic information.