On the Use of BERT for Automated Essay Scoring: Joint Learning of Multi-Scale Essay Representation
Abstract
In recent years, pre-trained models have become dominant in most natural language processing (NLP) tasks. However, in the area of Automated Essay Scoring (AES), pre-trained models such as BERT have not been properly used to outperform other deep learning models such as LSTM. In this paper, we introduce a novel multi-scale essay representation for BERT that can be jointly learned. We also employ multiple losses and transfer learning from out-of-domain essays to further improve the performance. Experiment results show that our approach derives much benefit from joint learning of multi-scale essay representation and obtains almost the state-of-the-art result among all deep learning models in the ASAP task. Our multi-scale essay representation also generalizes well to CommonLit Readability Prize data set, which suggests that the novel text representation proposed in this paper may be a new and effective choice for long-text tasks.
Keywords
Cite
@article{arxiv.2205.03835,
title = {On the Use of BERT for Automated Essay Scoring: Joint Learning of Multi-Scale Essay Representation},
author = {Yongjie Wang and Chuan Wang and Ruobing Li and Hui Lin},
journal= {arXiv preprint arXiv:2205.03835},
year = {2022}
}
Comments
Accepted to NAACL 2022 as a long paper