Comparative Evaluation of Pretrained Transfer Learning Models on Automatic Short Answer Grading
This work addresses grading efficiency for educators by providing an incremental comparison of existing models on a specific dataset.
The paper tackled automatic short answer grading by comparing pretrained transfer learning models (ELMo, BERT, GPT, GPT-2) using cosine similarity as a single feature, finding that ELMo outperformed the others on the Mohler dataset based on RMSE and correlation metrics.
Automatic Short Answer Grading (ASAG) is the process of grading the student answers by computational approaches given a question and the desired answer. Previous works implemented the methods of concept mapping, facet mapping, and some used the conventional word embeddings for extracting semantic features. They extracted multiple features manually to train on the corresponding datasets. We use pretrained embeddings of the transfer learning models, ELMo, BERT, GPT, and GPT-2 to assess their efficiency on this task. We train with a single feature, cosine similarity, extracted from the embeddings of these models. We compare the RMSE scores and correlation measurements of the four models with previous works on Mohler dataset. Our work demonstrates that ELMo outperformed the other three models. We also, briefly describe the four transfer learning models and conclude with the possible causes of poor results of transfer learning models.