Empowering Short Answer Grading: Integrating Transformer-Based Embeddings and BI-LSTM Network

Gomaa, Wael H.; Nagib, Abdelrahman E.; Saeed, Mostafa M.; Algarni, Abdulmohsen; Nabil, Emad

doi:10.3390/bdcc7030122

Open AccessArticle

Empowering Short Answer Grading: Integrating Transformer-Based Embeddings and BI-LSTM Network

by

Wael H. Gomaa

^1,2

,

Abdelrahman E. Nagib

²,

Mostafa M. Saeed

²,

Abdulmohsen Algarni

³

and

Emad Nabil

^4,5,*

¹

Faculty of Computers and Artificial Intelligence, Beni-Suef University, Beni Suef 62511, Egypt

²

Faculty of Computer Science, 6th of October Campus, MSA University, Giza 12566, Egypt

³

Faculty of Computer Science, King Khalid University, Abha 61421, Saudi Arabia

⁴

Faculty of Computer and Information Systems, Islamic University of Madinah, Madinah 42351, Saudi Arabia

⁵

Faculty of Computers and Artificial Intelligence, Cairo University, Giza 12613, Egypt

^*

Author to whom correspondence should be addressed.

Big Data Cogn. Comput. 2023, 7(3), 122; https://doi.org/10.3390/bdcc7030122

Submission received: 24 April 2023 / Revised: 8 June 2023 / Accepted: 15 June 2023 / Published: 21 June 2023

(This article belongs to the Special Issue Artificial Intelligence and Natural Language Processing)

Download

Browse Figures

Review Reports Versions Notes

Abstract

Automated scoring systems have been revolutionized by natural language processing, enabling the evaluation of students’ diverse answers across various academic disciplines. However, this presents a challenge as students’ responses may vary significantly in terms of length, structure, and content. To tackle this challenge, this research introduces a novel automated model for short answer grading. The proposed model uses pretrained “transformer” models, specifically T5, in conjunction with a BI-LSTM architecture which is effective in processing sequential data by considering the past and future context. This research evaluated several preprocessing techniques and different hyperparameters to identify the most efficient architecture. Experiments were conducted using a standard benchmark dataset named the North Texas Dataset. This research achieved a state-of-the-art correlation value of 92.5 percent. The proposed model’s accuracy has significant implications for education as it has the potential to save educators considerable time and effort, while providing a reliable and fair evaluation for students, ultimately leading to improved learning outcomes.

Keywords: automatic scoring; short answer grading; transformers; deep learning; AI in education

Share and Cite

MDPI and ACS Style

Gomaa, W.H.; Nagib, A.E.; Saeed, M.M.; Algarni, A.; Nabil, E. Empowering Short Answer Grading: Integrating Transformer-Based Embeddings and BI-LSTM Network. Big Data Cogn. Comput. 2023, 7, 122. https://doi.org/10.3390/bdcc7030122

AMA Style

Gomaa WH, Nagib AE, Saeed MM, Algarni A, Nabil E. Empowering Short Answer Grading: Integrating Transformer-Based Embeddings and BI-LSTM Network. Big Data and Cognitive Computing. 2023; 7(3):122. https://doi.org/10.3390/bdcc7030122

Chicago/Turabian Style

Gomaa, Wael H., Abdelrahman E. Nagib, Mostafa M. Saeed, Abdulmohsen Algarni, and Emad Nabil. 2023. "Empowering Short Answer Grading: Integrating Transformer-Based Embeddings and BI-LSTM Network" Big Data and Cognitive Computing 7, no. 3: 122. https://doi.org/10.3390/bdcc7030122

APA Style

Gomaa, W. H., Nagib, A. E., Saeed, M. M., Algarni, A., & Nabil, E. (2023). Empowering Short Answer Grading: Integrating Transformer-Based Embeddings and BI-LSTM Network. Big Data and Cognitive Computing, 7(3), 122. https://doi.org/10.3390/bdcc7030122

Article Menu

Empowering Short Answer Grading: Integrating Transformer-Based Embeddings and BI-LSTM Network

Abstract

Share and Cite

Article Metrics

Article Access Statistics

Further Information

Guidelines

MDPI Initiatives

Follow MDPI