BriefGPT.xyz
Sep, 2015
基于字符级卷积神经网络的文本分类
Character-level Convolutional Networks for Text Classification
HTML
PDF
Xiang Zhang, Junbo Zhao, Yann LeCun
TL;DR
本文通过构建大规模数据集，比较了基于字级别的卷积神经网络与传统模型如词袋、n-gram及基于词的卷积神经网络和循环神经网络在文本分类方面的表现。结果表明，基于字级别的卷积神经网络能够达到当前领域最佳或竞争性的结果。
Abstract
This article offers an empirical exploration on the use of
character-level convolutional networks
(ConvNets) for
text classification
. We constructed several large-scale datasets to show that
→