Paper Type
Short
Paper Number
1512
Description
This study aims to develop an automatic short-answer grading system. The focus is on achieving few-shot learning in short-answer grading, tackling the scarcity of labeled data. We utilize a two-head pseudo-Siamese neural network with an external knowledge model for transfer learning to enhance the system's ability to extract key information in the student answers for the automatic grading. The experiments are performed on real data, and the results show that the proposed system can effectively achieve the objective with a high accuracy.
Recommended Citation
Chang, Tzu-Lin; Lin, Keng-Pei; and Chen, Zong-Shun, "Automatic Short-Answer Grading with a Pseudo-Siamese Neural Network" (2024). PACIS 2024 Proceedings. 1.
https://aisel.aisnet.org/pacis2024/track14_educ/track14_educ/1
Automatic Short-Answer Grading with a Pseudo-Siamese Neural Network
This study aims to develop an automatic short-answer grading system. The focus is on achieving few-shot learning in short-answer grading, tackling the scarcity of labeled data. We utilize a two-head pseudo-Siamese neural network with an external knowledge model for transfer learning to enhance the system's ability to extract key information in the student answers for the automatic grading. The experiments are performed on real data, and the results show that the proposed system can effectively achieve the objective with a high accuracy.
When commenting on articles, please be friendly, welcoming, respectful and abide by the AIS eLibrary Discussion Thread Code of Conduct posted here.
Comments
Education