.png){kind=icon}
.png){kind=icon}
Return
LMTCSG: Multilabel Text Classification Combining Sequence-Based and GNN-Based Features
.png){kind=icon}
PRE
AI
DOI：10.1109/TII.2024.3465596.png)
.png){kind=icon}
Original request for help.png){kind=icon}
Share.png){kind=icon}
Save
Abstract
En 中文
Since multilabel text classification datasets often face the problem of label imbalance, therefore, using either sequence-based deep learning (DL) model or graph neural network (GNN)-based DL model alone will not achieve satisfactory classification results. To solve the above problem, firstly, two coattention networks are constructed to simultaneously obtain the sequence-based and GNN-based eigenvectors. Second, labels are added to the graph as global features, and a graph data augmentation strategy is proposed. When obtaining GNN-based eigenvectors, at first, connection and attention weights are obtained through adjacency matrix and the attention of neighborhoods. Then, node features are updated based on convolution and multihead attention, respectively. Multiple comparison experiments on four benchmark datasets prove that the model constructed in this article achieves the optimal classification results and can solve the label imbalance problem.
Keywords:
Vectors
Correlation
Convolution
Feature extraction
Data models
TV
Sun
Semantics
Recurrent neural networks
Informatics
Graph neural network (GNN)-based deep learning (DL) model
label imbalance problem
multilabel text classification (MLTC)
sequence-based deep learning (DL) model
Journal
IF:
9.9
Papers:
8.3K
Citations:
6.0W