4.3 Article

An attention-gated convolutional neural network for sentence classification

期刊

INTELLIGENT DATA ANALYSIS
卷 23, 期 5, 页码 1091-1107

出版社

IOS PRESS
DOI: 10.3233/IDA-184311

关键词

Sentence classification; convolutional neural network; NLReLU activation function; attention-gated convolutional neural network

资金

  1. Foundation for Innovative Research Groups of the National Natural Science Foundation of China [61521003]
  2. National Natural Science Foundation of China [61601513]

向作者/读者索取更多资源

The classification of sentences is very challenging, since sentences contain the limited contextual information. In this paper, we proposed an Attention-Gated Convolutional Neural Network (AGCNN) for sentence classification, which generates attention weights from the feature's context windows of different sizes by using specialized convolution encoders. It makes full use of limited contextual information to extract and enhance the influence of important features in predicting the sentence's category. Experimental results demonstrated that our model can achieve up to 3.1% higher accuracy than standard CNN models, and gain competitive results over the baselines on four out of the six tasks. Besides, we designed an activation function, namely, Natural Logarithm rescaled Rectified Linear Unit (NLReLU). Experiments showed that NLReLU can outperform ReLU and is comparable to other well-known activation functions on AGCNN.

作者

我是这篇论文的作者
点击您的名字以认领此论文并将其添加到您的个人资料中。

评论

主要评分

4.3
评分不足

次要评分

新颖性
-
重要性
-
科学严谨性
-
评价这篇论文

推荐

暂无数据
暂无数据