Abstract
Automated essay scoring aims to evaluate the quality of an essay automatically. It is one of the main educational application in the field of natural language processing. Recently, Pre-training techniques have been used to improve performance on downstream tasks, and many studies have attempted to use pre-training and then fine-tuning mechanisms in an essay scoring system. However, obtaining better features such as prompts by the pre-trained encoder is critical but not fully studied. In this paper, we create a prompt feature fusion method that is better suited for fine-tuning. Besides, we use multi-task learning by designing two auxiliary tasks, prompt prediction and prompt matching, to obtain better features. The experimental results show that both auxiliary tasks can improve model performance, and the combination of the two auxiliary tasks with the NEZHA pre-trained encoder produces the best results, with Quadratic Weighted Kappa improving 2.5% and Pearson’s Correlation Coefficient improving 2% on average across all results on the HSK dataset.
Funder
National Natural Science Foundation of China
Major Program of National Social Science Foundation of China
Subject
General Physics and Astronomy
Reference33 articles.
1. The imminence of… grading essays by computer;Page;Phi Delta Kappan,1966
2. Higgins, D., Burstein, J., Marcu, D., and Gentile, C. (2004, January 2–7). Evaluating multiple aspects of coherence in student essays. Proceedings of the NAACL-HLT, Boston, MA, USA.
3. Persing, I., and Ng, V. (2014, January 22–27). Modeling prompt adherence in student essays. Proceedings of the ACL, Baltimore, MD, USA.
4. Taghipour, K., and Ng, H.T. (2016, January 1–5). A neural approach to automated essay scoring. Proceedings of the EMNLP, Austin, TX, USA.
5. Dong, F., Zhang, Y., and Yang, J. (2017, January 3–4). Attention-based recurrent convolutional neural network for automatic essay scoring. Proceedings of the CoNLL, Vancouver, BC, Canada.
Cited by
1 articles.
订阅此论文施引文献
订阅此论文施引文献,注册后可以免费订阅5篇论文的施引文献,订阅后可以查看论文全部施引文献