Fine-grained essay scoring of a complex writing task for native speakers
Fine-grained essay scoring of a complex writing task for native speakers
复制标题
DOI：
10.18653/v1/w17-5040
复制
发表时间：
2017-09
期刊：
影响因子：
--
通讯作者：
Andrea Horbach;Dirk Scholten-Akoun;Yuning Ding;Torsten Zesch
中科院分区：
文献类型：
--
作者：
Andrea Horbach;Dirk Scholten-Akoun;Yuning Ding;Torsten Zesch
自动作文评分现在即使在高风险的测试中也被成功使用，但这主要限于学习者作文的整体评分。我们提出了一个新的数据集，由高度熟练的德语母语者撰写的文章，使用细粒度的标题进行评分，目的是提供详细的反馈。我们使用两种最先进的评分系统（神经和基于SVM的评分系统）进行的实验显示，与现有数据集相比，性能大幅下降。这表明需要这样的数据集，以指导更详细的论文评分方法的研究。
Automatic essay scoring is nowadays successfully used even in high-stakes tests, but this is mainly limited to holistic scoring of learner essays. We present a new dataset of essays written by highly proficient German native speakers that is scored using a fine-grained rubric with the goal to provide detailed feedback. Our experiments with two state-of-the-art scoring systems (a neural and a SVM-based one) show a large drop in performance compared to existing datasets. This demonstrates the need for such datasets that allow to guide research on more elaborate essay scoring methods.