Prediction of Category of Scientific Article by Graph Convolution
Prediction of Category of Scientific Article by Graph Convolution
复制标题
DOI：
10.1109/iiai-aai50415.2020.00023
复制
发表时间：
2020-09
期刊：
影响因子：
--
通讯作者：
S. Hirokawa;Takahiko Suzuki;Tetsuya Nakatoh
中科院分区：
文献类型：
--
作者：
S. Hirokawa;Takahiko Suzuki;Tetsuya Nakatoh
利用被引论文ID和被引论文ID的卷积方法可以提高论文类别的预测性能。本文提出了一种“词卷积”方法，不仅利用了被引论文的ID，而且还利用了这些论文中出现的词语。与现有方法相比，该方法对核心数据集的预测性能(准确率)提高了7%，对城市数据集的预测性能提高了12%，而对发布数据集的预测性能与现有方法相同。
The convolution method that uses the IDs of citing paper and cited paper is known to improve the prediction performance of category of papers. This paper proposes a "word convolution" method that uses not only the IDs of the cited and citing papers, but also the words that appear in those papers. The proposed method improves the prediction performance (accuracy) 7% for the core dataset and 12% for the citeseer dataset and gives the same performance for the pubmed dataset compared with the state-of-the-art method.