A Semantic Feature-Wise Transformation Relation Network for Automatic Short Answer Grading
A Semantic Feature-Wise Transformation Relation Network for Automatic Short Answer Grading
复制标题
DOI：
10.18653/v1/2021.emnlp-main.487
复制
发表时间：
2021
期刊：
影响因子：
--
通讯作者：
Zhaohui Li;Yajur Tomar;R. Passonneau
中科院分区：
文献类型：
--
作者：
Zhaohui Li;Yajur Tomar;R. Passonneau
自动简答评分（ASAG）是评估学生对客观问题的简短自然语言回答的任务。它是新教育平台的重要组成部分，可以支持更广泛地使用构造回答问题，以取代认知上挑战性较小的多项选择题。我们提出了一个语义智能转换关系网络（SFRN），更有效地利用ASAG数据集的多个组件。SFRN捕获问题（Q）、参考答案或标题（R）和标记的学生答案（A）之间的关系知识。关系网络学习QRA三元组元素的向量表示，然后使用学习的语义特征转换组合学习的表示。我们应用基于预处理的数据增强来解决训练数据有限和多类ASAG任务的高数据偏斜这两个问题。我们的模型在SemEval-2013基准数据集上的最新结果上有高达11%的性能提升，并超过了为Kaggle挑战设计的自定义方法，证明了其通用性。
Automatic short answer grading (ASAG) is the task of assessing students’ short natural language responses to objective questions. It is a crucial component of new education platforms, and could support more wide-spread use of constructed response questions to replace cognitively less challenging multiple choice questions. We propose a Semantic Feature-wise transformation Relation Network (SFRN) that exploits the multiple components of ASAG datasets more effectively. SFRN captures relational knowledge among the questions (Q), reference answers or rubrics (R), and labeled student answers (A). A relation network learns vector representations for the elements of QRA triples, then combines the learned representations using learned semantic feature-wise transformations. We apply translation-based data augmentation to address the two problems of limited training data, and high data skew for multi-class ASAG tasks. Our model has up to 11% performance improvement over state-of-the-art results on the benchmark SemEval-2013 datasets, and surpasses custom approaches designed for a Kaggle challenge, demonstrating its generality.