用元学习提升作文评分模型跨题目泛化能力
MAPLE: A Meta-learning Framework for Cross-Prompt Essay Scoring
- 基于原型网络设计元学习框架，学习跨题目的通用特征表示
- 在三个数据集上达到最优，最高提升8.5点（QWK）
- 适合需要统一评分标准的跨题目作文评估场景
自动作文评分（AES）在跨题目场景下面临挑战，即模型需对未见写作题目进行泛化。为此，我们提出MAPLE，一种基于原型网络的元学习框架，用于学习不同写作题目间的可迁移表征。在三个多样化数据集（ELLIPSE和ASAP（英文），LAILA（阿拉伯文））上，MAPLE在ELLIPSE和LAILA上均达到当前最优性能，分别在QWK指标上领先强基线8.5和3个百分点。在ASAP上，由于题目对应评分范围差异大，MAPLE在多个评价维度上实现提升，凸显了该方法在统一评分设置中的优势。结果表明，元学习在构建稳健的跨题目自动作文评分系统方面具有巨大潜力。
原文摘要 · Abstract (English)
Automated Essay Scoring (AES) faces significant challenges in cross-prompt settings, where models must generalize to unseen writing prompts. To address this limitation, we propose MAPLE, a meta-learning framework that leverages prototypical networks to learn transferable representations across different writing prompts. Across three diverse datasets (ELLIPSE and ASAP (English), and LAILA (Arabic)), MAPLE achieves state-of-the-art performance on ELLIPSE and LAILA, outperforming strong baselines by 8.5 and 3 points in QWK, respectively. On ASAP, where prompts exhibit heterogeneous score ranges, MAPLE yields improvements on several traits, highlighting the strengths of our approach in unified scoring settings. Overall, our results demonstrate the potential of meta-learning for building robust cross-prompt AES systems.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。