.png){kind=icon}
.png){kind=icon}
Return
Adaptive Dense Ensemble Model for Text Classification
.png){kind=icon}
PRE
AI
DOI：10.1109/TCYB.2021.3133106.png)
.png){kind=icon}
Original request for help.png){kind=icon}
Share.png){kind=icon}
Save
Abstract
En 中文
Text classification has been widely explored in natural language processing. In this article, we propose a novel adaptive dense ensemble model (AdaDEM) for text classification, which includes local ensemble stage (LES) and global dense ensemble stage (GDES). To strengthen the classification ability and robustness of the enhanced layer, we propose a selective ensemble model based on enhanced attention convolutional neural networks (EnCNNs). To increase the diversity of the ensemble system, these EnCNNs are generated by using two manners: 1) different sample subsets and 2) different granularity kernels. Then, an evaluation criterion that considers both accuracy and diversity is proposed in LES to obtain effective integration results. Furthermore, to make better use of information flow, we develop an adaptive dense ensemble structure with multiple enhanced layers in GDES to mitigate the issue that there may be redundant or invalid enhanced layers in the cascade structure. We conducted extensive experiments against state-of-the-art methods on multiple real-world datasets, including long and short texts, which has verified the effectiveness and generality of our method.
Keywords:
Convolutional neural networks
Feature extraction
Semantics
Adaptation models
Kernel
Deep learning
Text categorization
Adaptive dense ensemble
convolutional neural network (CNN)
enhanced attention
ensemble learning
text classification
Journal
IF:
10.5
Papers:
1.1W
Citations:
5.0W