期刊
NEUROCOMPUTING
卷 371, 期 -, 页码 39-50出版社
ELSEVIER
DOI: 10.1016/j.neucom.2019.09.012
关键词
Sentiment classification; Attention network; 2DCNN; Bidirectional GRU
资金
- Engineering and Technology Research Center of Guangdong Province for Logistics Supply Chain and Internet of Things [GDDST[2016]176]
- Provincial Science and Technology Project in Guangdong Province [2013B090200055]
- Key Laboratory of Cloud Computing for Super-integration Cloud Computing in Guangdong Province [610245048129]
Neural networks lately have achieved a great success on sentiment classification due to their ability of feature extraction. However, it remains as an enormous challenge to model long texts in document-level sentiment classification as well as to explore semantics between sentences and dependencies between features. Moreover, most existing methods can hardly differentiate the importance of different contents when constructing a document representation. To tackle these problems, we propose a novel neural network model: AttDR-2DCNN, which mainly consists of two parts. The first part utilizes a two-layer compositional bidirectional Gated Recurrent Unit (GRU) to obtain the compositional semantics of the document, where the first layer learns the feature vector of the sentence, and the second layer learns the document matrix representation consisting of two dimensions of the time-step dimension and feature dimension, from the sentence vectors. The second part applies a two-dimensional convolution operation and two-dimensional max pooling to capture more dependencies between sentences features. We further utilize different types of attention mechanism in these two parts to distinguish the importance of words, sentences and features in the document. Experiments are conducted on four publicly available document-level review datasets and the result shows that the proposed model outperforms some existing models. (C) 2019 Elsevier B.V. All rights reserved.
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。
推荐
暂无数据