Large-Scale Text Classification Using Scope-Based Convolutional Neural Network: A Deep Learning Approach

Large-Scale Text Classification Using Scope-Based Convolutional Neural Network: A Deep Learning Approach
复制标题

使用基于范围的卷积神经网络进行大规模文本分类:一种深度学习方法

DOI:
10.1109/access.2019.2955924
复制
发表时间:
2019
期刊:
影响因子:
3.9
通讯作者:
Liang Zhao
Liang Zhao
中科院分区:
计算机科学3区
文献类型:
--
作者:
Jiaying Wang;Yaxin Li;Jing Shan;Jinling Bao;Chuanyu Zong;Liang Zhao

文献摘要

被引文献

相似文献

文本分类是自然语言处理中最重要、最典型的任务之一,有着广泛的应用前景。近年来,深度学习方法在解决文本分类问题中显示出其优势,卷积神经网络(CNN)是该领域最成功的模型之一。本文提出了一种基于作用域卷积神经网络的文本分类深度学习方法。与基于窗口的CNN不同,作用域不要求构成局部特征的词必须是连续的。它可以表示文本数据更深层次的局部信息。提出了一种基于范围卷积的大规模卷积神经网络(LSS-CNN),它基于范围卷积、聚集优化和最大汇集运算。基于这些技术,我们可以逐步提取文本文档中最有价值的局部信息。本文还讨论了如何有效地计算大规模数据集的基于作用域的信息和并行训练。在真实数据集上进行了广泛的实验,将我们的模型与几种最先进的方法进行了比较。实验结果表明,LSS-CNN在处理大文本数据时既有效又具有良好的可扩展性。
Text classification is one of the most important and typical tasks in Natural Language Processing (NLP) which can be applied for many applications. Recently, deep learning approaches has shown their advantages in solving text classification problem, in which Convolutional Neural Network (CNN) is one of the most successful model in the field. In this paper, we propose a novel deep learning approach for categorizing text documents by using scope-based convolutional neural network. Different from window-based CNN, scope does not require the words that construct a local feature have to be contiguous. It can represent deeper local information of text data. We propose a large-scale scope-based convolutional neural network (LSS-CNN), which is based on scope convolution, aggregation optimization, and max pooling operation. Based on these techniques, we can gradually extract the most valuable local information of the text document. This paper also discusses how to effectively calculate the scope-based information and parallel training for large-scale datasets. Extensive experiments have been conducted on real datasets to compare our model with several state-of-the-art approaches. The experimental results show that LSS-CNN can achieve both effectiveness and good scalability on big text data.