Kaya, MustafaKavun, Mahir2026-09-012026-09-0120260306-45731873-5371http://dx.doi.org/10.1016/j.ipm.2026.104791https://hdl.handle.net/20.500.12403/8525This study proposes a new deep learning architecture for automated short-answer grading (ASAG) in Turkish. The model integrates transformer-based encoders (BERTurk, RoBERTa-Turkish (RoBERTa), ELECTRA-Turkish (ELECTRA)) with a Gated Multi-Scale Head Attention (GMHA) layer. Additionally, a BiLSTM network and parallel CNN layers are employed to capture both global dependencies and local linguistic patterns. The model was evaluated on a newly created Turkish dataset containing 2200 student responses from 220 learners, each graded by four experts. Among the pretrained Turkish encoders, the BERT-based model with GMHA achieved the best performance (QWK = 0.839, Pearson = 0.856, RMSE = 0.918). The model was also compared with traditional machine learning approaches and large language models (LLMs) using the Leave-One-Question-Out (LOQO) validation protocol. Under this setting, it achieved QWK = 0.337, Pearson = 0.468, and RMSE = 1.213, outperforming all baselines. Ablation studies confirmed the effectiveness of the GMHA and parallel CNN components. These results highlight both the theoretical contribution of multi-scale gated attention and the practical potential of developing reliable automated grading systems for morphologically rich, low-resource languages like Turkish.eninfo:eu-repo/semantics/closedAccessAutomatic Short Answer GradingTransformer ModelsGated Multi-Scale Head AttentionBilstmCnnArticle63710.1016/j.ipm.2026.1047912-s2.0-105035239903Q1WOS:001743136400001Q1