Autoregressive Score Generation for Multi-trait Essay Scoring

• DOI: 10.48550/arxiv.2403.08332
• Publication Date: 2024-01-01
• Authors: Do, Heejin; Kim, Yunsu; Lee, Gary Geunbae
• Keywords: FOS: Computer and information sciences; Computer Science - Computation and Language; Artificial Intelligence (cs.AI); Computer Science - Artificial Intelligence; Computation and Language (cs.CL)

Accepted at EACL2024 Findings<br/>Recently, encoder-only pre-trained models such as BERT have been successfully applied in automated essay scoring (AES) to predict a single overall score. However, studies have yet to explore these models in multi-trait AES, possibly due to the inefficiency of replicating BERT-based models for each trait. Breaking away from the existing sole use of encoder, we propose an autoregressive prediction of multi-trait scores (ArTS), incorporating a decoding process by leveraging the pre-trained T5. Unlike prior regression or classification methods, we redefine AES as a score-generation task, allowing a single model to predict multiple scores. During decoding, the subsequent trait prediction can benefit by conditioning on the preceding trait scores. Experimental results proved the efficacy of ArTS, showing over 5% average improvements in both prompts and traits.<br/>