Chinese text classification based on character-level CNN and SVM
Chinese text classification based on character-level CNN and SVM
复制标题
DOI：
10.1007/978-981-13-6473-0_20
复制
发表时间：
2019-10
期刊：
影响因子：
--
通讯作者：
Huaiguang Wu;Daiyi Li;Ming Cheng
中科院分区：
文献类型：
--
作者：
Huaiguang Wu;Daiyi Li;Ming Cheng
针对传统的基于词频-逆文档频（TF-IDF）的SVM分类算法存在维数灾难、数据稀疏、计算时间长等问题，提出了一种新的不依赖于人工设计特征和领域知识的混合中文文本分类系统：CSVM。首先，通过为输入语言构建大小为m的文本词汇表来完成编码单词，然后使用1-of-m编码来量化每个单词。其次，利用卷积神经网络（CNN）提取每个词的特征向量的形态特征，然后通过大规模文本训练得到每个词向量的语义特征。最后，利用SVM多分类器对文本进行分类。实验结果表明，CSVM算法比其他传统的中文文本分类算法更有效。
Aiming at the problems of curse of dimensionality, sparse data and long computation time in traditional SVM classification algorithm based on term frequency-inverse document frequency (TF-IDF), we propose a novel hybrid system for Chinese text classification: CSVM, which is independent of the hand-designed features and domain knowledge. Firstly, the encoding words are done by constructing a text vocabulary of size m for the input language, and then quantise each word using 1-of-m encoding. Secondly, we exploit the convolutional neural network (CNN) to extract the morphological features of character vectors from each word, and then through large scale text material training the semantic feature of each word vectors are be obtained the semantic feature of each word vectors. Finally, the text classification is carried out with the SVM multiple classifier. The experimental results show that the CSVM algorithm is more effective than other traditional Chinese text classification algorithm.