Autoregressive Score Generation for Multi-trait Essay Scoring
This work addresses the inefficiency of replicating models for each trait in automated essay scoring, offering a more streamlined solution for educational assessment.
The paper tackled the problem of multi-trait automated essay scoring by proposing an autoregressive score-generation method, which achieved over 5% average improvements in both prompts and traits compared to existing approaches.
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.