Results and Insights from Diagnostic Questions: The NeurIPS 2020 Education Challenge
Results and Insights from Diagnostic Questions: The NeurIPS 2020 Education Challenge
复制标题
诊断问题的结果和见解：NeurIPS 2020 教育挑战赛
DOI：
--
复制
发表时间：
2021
期刊：
影响因子：
--
通讯作者：
Cheng Zhang
中科院分区：
文献类型：
--
作者：
Zichao Wang;A. Lamb;Evgeny S. Saveliev;Pashmina Cameron;Yordan Zaykov;José Miguel Hernández;Richard E. Turner;Richard Baraniuk;Craig Barton;Simon L. Peyton Jones;Simon Woodhead;Cheng Zhang
这场比赛涉及教育诊断问题，这是教学有效的，多项选择题（MCQ）的干扰体现误解。随着大量的和不断增加的此类问题，它成为压倒性的教师知道哪些问题是最好的学生使用。因此，我们试图回答以下问题：在手动个性化不可行的大规模学习场景中，我们如何使用数亿个MCQ答案的数据来驱动自动个性化学习？成功大规模使用MCQ数据有助于构建更智能、个性化的学习平台，最终提高教育质量。为此，我们引入了一个新的，大规模的，真实世界的数据集，并在MCQ上制定了4个数据挖掘任务，这些任务模拟了真实的学习场景，并在NeurIPS 2020的竞赛环境中针对上述问题的各个方面。我们报告我们的NeurIPS比赛中，近400支球队提交了约4000份意见书，与我们的每一个任务的多样性和有效的方法。
This competition concerns educational diagnostic questions, which are pedagogically effective, multiple-choice questions (MCQs) whose distractors embody misconceptions. With a large and ever-increasing number of such questions, it becomes overwhelming for teachers to know which questions are the best ones to use for their students. We thus seek to answer the following question: how can we use data on hundreds of millions of answers to MCQs to drive automatic personalized learning in large-scale learning scenarios where manual personalization is infeasible? Success in using MCQ data at scale helps build more intelligent, personalized learning platforms that ultimately improve the quality of education en masse. To this end, we introduce a new, large-scale, real-world dataset and formulate 4 data mining tasks on MCQs that mimic real learning scenarios and target various aspects of the above question in a competition setting at NeurIPS 2020. We report on our NeurIPS competition in which nearly 400 teams submitted approximately 4000 submissions, with encouragingly diverse and effective approaches to each of our tasks.