知识主题间先序关系挖掘

麻珂欣,魏笔凡,马杰,刘均,黄毅,胡珉,冯俊兰

Mining prerequisite relations among learning objects

Kexin MA,Bifan WEI,Jie MA,Jun LIU,Yi HUANG,Min HU,Junlan FENG

表2 对比实验结果（准确率）

领域 MaxEnt RefD MLP 端到端模型 相同权重策略 不同权重策略 减数分裂 51.0% 55.7% 79.0% 65.7% 77.12% 公钥加密 67.1% 57.7% 58.0% 72.4% 85.93% 平行假设 64.7% 67.9% 85.0% 51.7% 80.79% 牛顿定律 53.9% 64.6% 68.0% 45.5% 86.99% 全球变暖 56.8% 60.1% 82.0% 33.5% 84.26% 平均 58.7% 61.2% 74.4% 53.8% 83.02%