On the Use of BERT for Automated Essay Scoring: Joint Learning of Multi-Scale Essay Representation
This work addresses the challenge of effectively using pre-trained models like BERT for AES, which is important for educational technology, though it is incremental as it builds on existing BERT methods.
The paper tackled the problem of Automated Essay Scoring (AES) by introducing a novel multi-scale essay representation for BERT, achieving almost state-of-the-art results on the ASAP task and generalizing well to the CommonLit Readability Prize dataset.
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.