当前位置: X-MOL 学术Int. J. Mach. Learn. & Cyber. › 论文详情
Our official English website, www.x-mol.net, welcomes your feedback! (Note: you will need to create a separate account there.)
Attentive convolutional gated recurrent network: a contextual model to sentiment analysis
International Journal of Machine Learning and Cybernetics ( IF 5.6 ) Pub Date : 2020-06-08 , DOI: 10.1007/s13042-020-01135-1
Olivier Habimana , Yuhua Li , Ruixuan Li , Xiwu Gu , Wenjin Yan

Considering contextual features is a key issue in sentiment analysis. Existing approaches including convolutional neural networks (CNNs) and recurrent neural networks (RNNs) lack the ability to account and prioritize informative contextual features that are necessary for better sentiment interpretation. CNNs present limited capability since they are required to be very deep, which can lead to the gradient vanishing whereas, RNNs fail because they sequentially process input sequences. Furthermore, the two approaches treat all words equally. In this paper, we suggest a novel approach named attentive convolutional gated recurrent network (ACGRN) that alleviates the above issues for sentiment analysis. The motivation behind ACGRN is to avoid the vanishing gradient caused by deep CNN via applying a shallow-and-wide CNN that learns local contextual features. Afterwards, to solve the problem caused by the sequential structure of RNN and prioritizing informative contextual information, we use a novel prior knowledge attention based bidirectional gated recurrent unit (ATBiGRU). Prior knowledge ATBiGRU captures global contextual features with a strong focus on the previous hidden states that carry more valuable information to the current time step. The experimental results show that ACGRN significantly outperforms the baseline models over six small and large real-world datasets for the sentiment classification task.



中文翻译:

细观卷积门控递归网络:情感分析的上下文模型

考虑上下文特征是情感分析中的关键问题。包括卷积神经网络(CNN)和递归神经网络(RNN)在内的现有方法都缺乏解释和优先考虑信息上下文特征的能力,而这些对于更好的情感解释是必不可少的。由于CNN要求非常深,因此它们的功能有限,这可能导致梯度消失,而RNN失败是因为它们顺序处理输入序列。此外,两种方法均等地对待所有单词。在本文中,我们提出了一种名为注意力卷积门控递归网络(ACGRN)的新颖方法,该方法可缓解上述问题以进行情感分析。ACGRN背后的动机是通过应用学习局部上下文特征的浅而宽的CNN来避免由深层CNN引起的消失梯度。然后,为了解决由RNN的顺序结构引起的问题并优先提供信息性上下文信息,我们使用了一种基于先验知识注意力的双向门控循环单元(ATBiGRU)。先验知识ATBiGRU捕获全局上下文特征,重点关注以前的隐藏状态,这些隐藏状态将更多有价值的信息传送到当前时间步长。实验结果表明,对于情感分类任务,ACGRN在六个大型现实数据集上均明显优于基线模型。我们使用一种新颖的基于先验知识注意力的双向门控递归单元(ATBiGRU)。先验知识ATBiGRU捕获全局上下文特征,重点关注以前的隐藏状态,这些隐藏状态将更多有价值的信息传送到当前时间步长。实验结果表明,对于情感分类任务,ACGRN在六个大型现实数据集上均明显优于基线模型。我们使用一种新颖的基于先验知识注意力的双向门控递归单元(ATBiGRU)。先验知识ATBiGRU捕获全局上下文特征,重点关注以前的隐藏状态,这些隐藏状态将更多有价值的信息传送到当前时间步长。实验结果表明,对于情感分类任务,ACGRN在六个大型现实数据集上均明显优于基线模型。

更新日期:2020-06-08
down
wechat
bug