基于多依赖图和知识融合的方面级情感分析模型

何勇禧,韩虎,孔博

Aspect-based sentiment analysis model based on multi-dependency graph and knowledge fusion

Yongxi HE,Hu HAN,Bo KONG

表 3 不同模型在5个数据集上的分类准确率和宏观F1 分数对比

Tab.3 Comparison of classification accuracy and macro F1 score of different models in five datasets

% 类别 模型 Twitter Laptop14 Restaurant14 Restaurant15 Restaurant16 Acc MF1 Acc MF1 Acc MF1 Acc MF1 Acc MF1 GloVe LSTM 69.56 67.70 69.28 63.09 78.13 67.47 77.37 55.17 86.80 63.88 IAN 72.50 70.81 72.05 67.38 79.26 70.09 78.54 52.65 84.74 55.21 ASGCN 72.15 70.40 75.55 71.05 80.77 72.02 79.89 61.89 88.99 67.48 kumaGCN 72.45 70.77 76.12 72.42 81.43 73.64 80.69 65.99 89.39 73.19 SKGCN 71.97 70.22 73.20 69.18 80.36 70.43 80.12 60.70 85.17 68.08 CDT 72.87 71.40 75.89 71.84 81.46 73.59 80.25 61.92 86.65 70.18 MI-GCN 73.31 72.12 76.59 72.44 82.32 74.31 80.81 64.21 89.50 71.97 DGAT 73.99 72.53 76.49 72.75 82.68 75.53 — — — — MDKGCN 74.28 72.68 78.06 74.61 82.41 74.34 81.92 66.85 90.26 75.52 BERT BERT-BASE 73.70 71.50 77.74 73.30 82.68 73.54 81.34 63.57 88.89 68.19 SK-GCN-BERT 75.00 73.01 79.00 75.57 83.48 75.19 83.20 66.78 87.19 72.02 WGAT-BERT 76.25 74.56 80.49 77.21 85.71 80.23 — — — — SSEMGAT-BERT 76.81 76.10 80.06 76.78 86.42 79.70 — — — — MFSGC-BERT 75.41 72.98 78.53 74.91 85.71 79.55 83.58 68.37 91.07 76.09 MDKGCN-BERT 76.30 75.31 80.41 77.60 86.70 80.93 85.61 72.54 91.07 76.70