Grading short answer questions automatically with interpretable reasoning
behind the grading decision is a challenging goal for current transformer
approaches. Justification cue detection, in combination with logical reasoners,
has shown a promising direction for neuro-symbolic architectures in ASAG. But,
one of the main challenges is the requirement of annotated justification cues
in the students' responses, which only exist for a few ASAG datasets. To
overcome this challenge, we contribute (1) a weakly supervised annotation
procedure for justification cues in ASAG datasets, and (2) a neuro-symbolic
model for explainable ASAG based on justification cues. Our approach improves
upon the RMSE by 0.24 to 0.3 compared to the state-of-the-art on the Short
Answer Feedback dataset in a bilingual, multi-domain, and multi-question
training setup. This result shows that our approach provides a promising
direction for generating high-quality grades and accompanying explanations for
future research in ASAG and educational NLP.

自动评分短问答题并解释评分决策是当下转换器方法的一项具有挑战性的目标。在 ASAG 中，自动检测评分理由并与逻辑推理相结合已经展现出一种有希望的方向，但主要挑战之一是要求学生回答中存在经过注解的评分理由，而这种注解在现有 ASAG 数据集中只有很少。为解决这个挑战，我们提出了（1）一种适用于 ASAG 数据集中评分理由的弱监督注解过程，以及（2）一种基于评分理由的可解释 ASAG 的神经符号模型。在双语、多领域、多问题的训练设置中，与现有最先进技术相比，我们的方法将均方根误差（RMSE）提高了 0.24 至 0.3。这个结果表明我们的方法为 ASAG 和教育 NLP 领域的未来研究提供了一个有前景的方向，能够生成高质量的成绩和相应的解释。