Gated Convolutional Neural Networks for Text Classification

扫码查看

原文链接

NETL

外文摘要：The popular approach for several natural language processing tasks involves deep neural networks， and in particular， recurrent neural networks (RNNs) and convolutional neural networks (CNNs)。 While RNNs can capture the dependency in a sequence of arbitrary length， CNNs are suitable for extracting position-invariant features。 In this study， a state-of-the-art CNN model incorporating a gate mechanism that is typically used in RNNs， is adapted to text classification tasks。 The incorporated gate mechanism allows the CNNs to better select which features or words are relevant for predicting the corresponding class。 Through experiments on various large datasets， it was found that the introduction of a gate mechanism into CNNs can improve the accuracy of text classification tasks such as sentiment classification， topic classification， and news categorization。

外文关键词：

Gate mechanismConvolutional neural networksText classification

作者：

Jin Sun、Rize Jin、Xiaohan Ma、Joon-young Park、Kyung-ah Sohn、Tae-sun Chung

展开 >

作者单位：

Computer Engineering, Ajou University, Suwon-si, Gyeonggi-do 16499, Korea

School of Computer Science and Software Engineering, Tianjin Polytechnic University, Tianjin 300160, China

会议名称：

International Conference on Computer Science and its Applications;International Conference on Ubiquitous Information Technologies and Applications

会议地点：

Macao(CN)

会议母体文献：

Advances in Computer Science and Ubiquitous Computing

页码：

309-316

出版时间：

2019

DOI：

10.1007/978-981-15-9343-7_43