Title | Chinese Texts Classification System |
Publication Type | Conference Paper |
Year of Publication | 2019 |
Authors | Zhu, Meng, Yang, Xudong |
Conference Name | 2019 IEEE 2nd International Conference on Information and Computer Technologies (ICICT) |
Date Published | mar |
Keywords | automatic Chinese text classification system, automatic system, based algorithms, Bayes methods, Classification algorithms, CNN, convolution, Deep Learning, deep learning field, feature extraction, hierarchy conception, Human Behavior, k-Bayes algorithm, learning (artificial intelligence), machine learning, machine learning field, naive Bayes, natural language processing, NB method, neural nets, pattern classification, probability, pubcrawl, Resiliency, Scalability, text analysis, Training |
Abstract | In this article, we designed an automatic Chinese text classification system aiming to implement a system for classifying news texts. We propose two improved classification algorithms as two different choices for users to choose and then our system uses the chosen method for the obtaining of the classified result of the input text. There are two improved algorithms, one is k-Bayes using hierarchy conception based on NB method in machine learning field and another one adds attention layer to the convolutional neural network in deep learning field. Through experiments, our results showed that improved classification algorithms had better accuracy than based algorithms and our system is useful for making classifying news texts more reasonably and effectively. |
DOI | 10.1109/INFOCT.2019.8710894 |
Citation Key | zhu_chinese_2019 |