Comparative Evaluation of Pretrained Transfer Learning Models on Automatic Short Answer Grading

TL;DR

This paper compares pretrained transfer learning models ELMo, BERT, GPT, and GPT-2 for automatic short answer grading, finding ELMo performs best using cosine similarity on the Mohler dataset.

Contribution

It evaluates the effectiveness of four pretrained transfer learning models for ASAG using a simple cosine similarity approach, highlighting ELMo's superior performance.

Findings

ELMo outperforms BERT, GPT, and GPT-2 on the Mohler dataset.

Using a single cosine similarity feature is effective for ASAG.

Transfer learning models show varying effectiveness, with ELMo leading.

Abstract

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.