Tapping the Potential of Coherence and Syntactic Features in Neural Models for Automatic Essay Scoring
Reviewed by Pith T0 review T1 audit T2 compute T3 formal T4 kernel pith:KOHECWDUrecord.jsonopen to challenge →
read the original abstract
In the prompt-specific holistic score prediction task for Automatic Essay Scoring, the general approaches include pre-trained neural model, coherence model, and hybrid model that incorporate syntactic features with neural model. In this paper, we propose a novel approach to extract and represent essay coherence features with prompt-learning NSP that shows to match the state-of-the-art AES coherence model, and achieves the best performance for long essays. We apply syntactic feature dense embedding to augment BERT-based model and achieve the best performance for hybrid methodology for AES. In addition, we explore various ideas to combine coherence, syntactic information and semantic embeddings, which no previous study has done before. Our combined model also performs better than the SOTA available for combined model, even though it does not outperform our syntactic enhanced neural model. We further offer analyses that can be useful for future study.
This paper has not been read by Pith yet.
discussion (0)
Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.