iAttention Transformer: An Inter-Sentence Attention Mechanism for Automated Grading

Ibidapo Dare Dada (), Adio T. Akinwale, Idowu A. Osinuga, Henry Nwagu Ogbu and Ti-Jesu Tunde-Adeleke
Additional contact information
Ibidapo Dare Dada: Department of Computer and Information Sciences, Covenant University, Ota P.M.B. 1023, Ogun State, Nigeria
Adio T. Akinwale: Department of Computer Science, Federal University of Agriculture, Abeokuta P.M.B 2240, Ogun State, Nigeria
Idowu A. Osinuga: Department of Mathematics, Federal University of Agriculture, Abeokuta P.M.B 2240, Ogun State, Nigeria
Henry Nwagu Ogbu: Department of Computer and Information Sciences, Covenant University, Ota P.M.B. 1023, Ogun State, Nigeria
Ti-Jesu Tunde-Adeleke: Department of Computer and Information Sciences, Covenant University, Ota P.M.B. 1023, Ogun State, Nigeria

Mathematics, 2025, vol. 13, issue 18, 1-31

Abstract: This study developed and evaluated transformer-based models enhanced with inter-sentence attention (iAttention) mechanisms to improve the automatic grading of student responses to open-ended questions. Traditional transformer models emphasize intra-sentence relationships and often fail to capture complex semantic alignments needed for accurate assessment. To overcome this limitation, three iAttention mechanisms, including i A t t e n t i o n T F − I D F , i A t t e n t i o n w o r d and i A t t e n t i o n H W were proposed to enhance the model’s capacity to align key ideas between students and reference answers. This helps improve the model’s ability to capture important semantic relationships between words in two sentences. Unlike previous approaches that rely solely on aggregated sentence embeddings, the proposed method introduces inter-sentence attention layers that explicitly model semantic correspondence between individual sentences. This enables finer-grained matching of key concepts, reasoning, and logical structure which are crucial for fair and reliable assessment. The models were evaluated on multiple benchmark datasets, including Semantic Textual Similarity (STS), SemEval-2013 Beetle, SciEntsBank, Mohler, and a composite of university-level educational datasets (U-datasets). Experimental results demonstrated that integrating iAttention consistently outperforms baseline models, achieving higher Pearson and Spearman Correlation scores on STS, Mohler, and U-datasets, as well as superior Macro-F1, Weighted-F1, and Accuracy on the Beetle and SciEntsBank datasets. This approach contributes to the development of scalable, consistent, and fair automated grading systems by narrowing the gap between machine evaluation and human judgment, ultimately leading to more accurate and efficient assessment practices.

Keywords: automated grading systems (AGS); attention mechanisms; machine learning in education; natural language processing (NLP) (search for similar items in EconPapers)
JEL-codes: C (search for similar items in EconPapers)
Date: 2025
References: View complete reference list from CitEc
Citations:

Downloads: (external link)
https://www.mdpi.com/2227-7390/13/18/2991/pdf (application/pdf)
https://www.mdpi.com/2227-7390/13/18/2991/ (text/html)

Related works:
This item may be available elsewhere in EconPapers: Search for items with the same title.

Export reference: BibTeX RIS (EndNote, ProCite, RefMan) HTML/Text

Persistent link: https://EconPapers.repec.org/RePEc:gam:jmathe:v:13:y:2025:i:18:p:2991-:d:1750354

Access Statistics for this article

Mathematics is currently edited by Ms. Emma He

More articles in Mathematics from MDPI
Bibliographic data for series maintained by MDPI Indexing Manager ().