Towards Prompt Generalization: Grammar-aware Cross-Prompt Automated Essay Scoring
This addresses the practical applicability of automated essay scoring for educational or assessment systems, but it is incremental as it builds on prior cross-prompt methods.
The paper tackled the problem of automated essay scoring in cross-prompt settings where essays are scored on unseen prompts, and the result was that their proposed method, GAPS, achieved notable QWK gains in the most challenging cross-prompt scenario.
In automated essay scoring (AES), recent efforts have shifted toward cross-prompt settings that score essays on unseen prompts for practical applicability. However, prior methods trained with essay-score pairs of specific prompts pose challenges in obtaining prompt-generalized essay representation. In this work, we propose a grammar-aware cross-prompt trait scoring (GAPS), which internally captures prompt-independent syntactic aspects to learn generic essay representation. We acquire grammatical error-corrected information in essays via the grammar error correction technique and design the AES model to seamlessly integrate such information. By internally referring to both the corrected and the original essays, the model can focus on generic features during training. Empirical experiments validate our method's generalizability, showing remarkable improvements in prompt-independent and grammar-related traits. Furthermore, GAPS achieves notable QWK gains in the most challenging cross-prompt scenario, highlighting its strength in evaluating unseen prompts.