Journal ArticleDOI
Using Maximum Entropy Model for Chinese Text Categorization
About:
This article is published in Journal of Computer Research and Development.The article was published on 2005-01-15. It has received 47 citations till now. The article focuses on the topics: Principle of maximum entropy & n-gram.read more
Citations
More filters
Journal ArticleDOI
Latent semantic analysis for text categorization using neural network
Bo Yu,Zongben Xu,Cheng-hua Li +2 more
TL;DR: Experimental results show that the models using MBPNN outperform than the basic BPNN and the application of LSA for this system can lead to dramatic dimensionality reduction while achieving good classification results.
Journal ArticleDOI
Advances in Machine Learning Based Text Categorization
Su Jinshu,Zhang Bofeng,Xu Xin +2 more
TL;DR: It is pointed out that problems such as nonlinearity, skewed data distribution, labeling bottleneck, hierarchical categorization, scalability of algorithms and categorization of Web pages are the key problems to the study of text categorization.
Journal ArticleDOI
Attention-based BiGRU-CNN for Chinese question classification
TL;DR: A novel deep neural network model is proposed, Attention-Based BiGRU-CNN network (ABBC), which combines the characteristics and advantages of convolutional neural network, attention mechanism and recurrent neural network and achieves the best performance in the Chinese question classification task.
Proceedings ArticleDOI
LSTM-CNN Hybrid Model for Text Classification
TL;DR: A hybrid model of LSTM and CNN is proposed that can effectively improve the accuracy of text classification and the performance of the hybrid model is compared with that of other models in the experiment.
Journal ArticleDOI
Text categorization based on combination of modified back propagation neural network and latent semantic analysis
TL;DR: The MBPNN is proposed to accelerate the training speed of BPNN and improve the categorization accuracy, and the application of LSA for the system can lead to dramatic dimensionality reduction while achieving good classification results.