多视角网页分类数据集构建及性能评估

孙辰星, 刘伟, 卢彬, 梁诗宇, 诸云强, 甘小莺

Multi⁃view webpage classification dataset construction and evaluation

Chenxing Sun, Wei Liu, Bin Lu, Shiyu Liang, Yunqiang Zhu, Xiaoying Gan

表3 多种基准算法在本文Web?Minds上的网页类型分类性能

Table 3 Performance of webpage classification by different benchmark algorithms on our Web?Minds

方法 Acc Pre R F1⁃score LR 65.26% 70.44% 70.52% 0.7048 SVM 68.31% 72.42% 75.04% 0.7371 BERT 76.65% 82.18% 86.53% 0.8430 RoBERTa 76.56% 81.89% 86.12% 0.8395 XLNet 75.08% 82.03% 85.89% 0.8392 RiSER 70.33% 76.54% 79.21% 0.7785 DC⁃F 70.29% 79.34% 83.27% 0.8126 SMGCN 78.04% 83.11% 87.76% 0.8537 Fusion 82.14% 84.89% 90.75% 0.8772