基于深度信念网络的文本分类算法① - 计算机系统应用.pdf

2015 年 第 24 卷 第 2 期 计 算 机 系 统 应 用 ① 基于深度信念网络的文本分类算法 陈翠平 ( 同济大学 计算机软件与理论系, 上海 201804) 摘 要: 随着网络的迅猛发展, 文本分类成为处理和组织大量文档数据的关键技术. 目前已经有许多不同类型的 神经网络应用于文本分类, 并且取得良好的效果. 但是, 大部分模型仅采用文档的少量特征作为输入, 没有考虑 到足够的信息量; 而当考虑到足够的特征时, 又会发生维数灾难, 导致模型难以训练或者训练时间大幅增加. 利 用深度信念网络从文本中抽取特征, 并利用 softmax 回归分类器对抽取后的特征分类. 深度信念网络不仅具有强 大的学习能力, 同时还能从高维的原始特征中抽取低维度高度可区分的低维特征, 因此利用深度信念网络来对 文本分类, 不仅能够考虑到文档的足够的信息量, 而且能够快速的训练. 并且实验结果也表明利用深度信念网络 实现文本分类的性能很好. 关键词: 文本分类; 受限玻尔兹曼机; 深度信念网络; softmax 回归分类器; 文本特征. Text Categorization Based on Deep Belief Network CHEN Cui-Ping (Department of Computer Science and Technology, Tongji University, Shanghai 201804, China) Abstract: With the rapid development of the network, text categorization has become a key technology in processing and organizing large text. There are already many different types of neural networks applied to text categorization and achieve good results. However, most of the document models use only a small amount of features as input which don’t take into account the sufficient amount of information. Considering enough characteristics, the dimensions of the disaster will occur, and resulting in a substantial increase training time, difficulty in training the model. This paper considers using deep belief networks to extract features from the text, then using softmax regression classifier for classification. The deep belief networks not only has a high learning ability, but also can extract highly distinguishable and low-dimensional features from the original high-dimensional features. So taking advantage of the deep belief networks to classify the text, can take into account enough information document amount. And the r