Autoregressive Score Generation for Multi-trait Essay Scoring

arXiv:2403.08332v1 Announce Type: new
Abstract: 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 …

abstract arxiv automated bert breaking cs.ai cs.cl encoder essay explore however pre-trained models scoring studies type