标题:A Self-attention Based LSTM Network for Text Classification
作者:Jing, Ran
通讯作者:Jing, Ran
作者机构:[Jing, Ran ] School of Control Science and Engineering, Shandong University, Jinan, China
会议名称:2019 3rd International Conference on Control Engineering and Artificial Intelligence, CCEAI 2019
会议日期:January 24, 2019 - January 26, 2019
来源:Journal of Physics: Conference Series
出版年:2019
卷:1207
期:1
DOI:10.1088/1742-6596/1207/1/012008
摘要:Neural networks have been used to achieve impressive performance in Natural Language Processing (NLP). Among all algorithms, RNN is a widely used architecture for text classification tasks. The main challenge in sentiment classification is the quantification of the connections between context words in a sentence. Even though various types and structures of model have been proposed, they encounter the problem of gradient vanishing and are unlikely to show the full potential of the network. In this work, we present a new RNN model based on the self-attention mechanism to improve the performance while dealing with long sentences and whole documents. Empirical results show that our model outperforms the state-of-art algorithms.
© Published under licence by IOP Publishing Ltd.
收录类别:EI
资源类型:会议论文
TOP