arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 1807.09602cs.CL
收藏

基于多块卷积高速公路的文本分类

Text Classification based on Multiple Block Convolutional Highways

University of Waterloo(滑铁卢大学);University of Tehran(德黑兰大学)

Seyed Mahdi Rezaeinia, Ali Ghodsi, Rouhollah Rahmani

摘要:

在情感分析、主观/客观分析和意见极性等文本分类领域,卷积神经网络因其性能和准确性而受到特别关注。在这项工作中,我们应用了CNN的最新进展,并提出了一种新的架构,多块卷积高速公路(MBCH),与以前的架构相比,它在多个流行的基准数据集上实现了更高的精度。MBCH基于新的技术和架构,包括高速公路网络、DenseNet、批量归一化和瓶颈层。此外,为了应对用作CNN输入的现有预训练词向量的局限性,我们提出了一种新方法,即改进的词向量(IWV)。IWV提高了用于文本分类任务的CNN的准确性。

英文摘要:

In the Text Classification areas of Sentiment Analysis, Subjectivity/Objectivity Analysis, and Opinion Polarity, Convolutional Neural Networks have gained special attention because of their performance and accuracy. In this work, we applied recent advances in CNNs and propose a novel architecture, Multiple Block Convolutional Highways (MBCH), which achieves improved accuracy on multiple popular benchmark datasets, compared to previous architectures. The MBCH is based on new techniques and architectures including highway networks, DenseNet, batch normalization and bottleneck layers. In addition, to cope with the limitations of existing pre-trained word vectors which are used as inputs for the CNN, we propose a novel method, Improved Word Vectors (IWV). The IWV improves the accuracy of CNNs which are used for text classification tasks.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑