教师制作的大规模完形填空题集
Large-scale Cloze Test Dataset Created by Teachers
摘要：
完形填空是语言考试中广泛采用的一种测试形式，用来评估学生的语言水平。在本文中，我们提出了第一个大规模的人类创造的完形填空测试数据集CLOTH，包含在初中和高中语言考试中使用的问题。由于教师精心创建了缺失的空白，而考生的选择则被故意设计得细致入微，因此，与以前自动生成的完形填空数据集相比，CLOTH需要更深的语言理解和更宽的注意力跨度。我们测试了专门设计的基线模型的性能，包括在10亿单词语料库上训练的语言模型，并显示人类的表现远远优于它们。我们调查的性能差距的来源，跟踪模型的缺陷，一些独特的属性的CLOTH，并确定有限的理解能力的长期背景下的关键瓶颈。
英文摘要：
Cloze tests are widely adopted in language exams to evaluate students' language proficiency. In this paper, we propose the first large-scale human-created cloze test dataset CLOTH, containing questions used in middle-school and high-school language exams. With missing blanks carefully created by teachers and candidate choices purposely designed to be nuanced, CLOTH requires a deeper language understanding and a wider attention span than previously automatically-generated cloze datasets. We test the performance of dedicatedly designed baseline models including a language model trained on the One Billion Word Corpus and show humans outperform them by a significant margin. We investigate the source of the performance gap, trace model deficiencies to some distinct properties of CLOTH, and identify the limited ability of comprehending the long-term context to be the key bottleneck.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
