当前位置: X-MOL 学术Sci. Program. › 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.)
Deep Learning Structure for Cross-Domain Sentiment Classification Based on Improved Cross Entropy and Weight
Scientific Programming ( IF 1.672 ) Pub Date : 2020-06-29 , DOI: 10.1155/2020/3810261
Rong Fei 1 , Quanzhu Yao 1 , Yuanbo Zhu 2 , Qingzheng Xu 3 , Aimin Li 1 , Haozheng Wu 1 , Bo Hu 4
Affiliation  

Within the sentiment classification field, the convolutional neural network (CNN) and long short-term memory (LSTM) are praised for their classification and prediction performance, but their accuracy, loss rate, and time are not ideal. To this purpose, a deep learning structure combining the improved cross entropy and weight for word is proposed for solving cross-domain sentiment classification, which focuses on achieving better text sentiment classification by optimizing and improving recurrent neural network (RNN) and CNN. Firstly, we use the idea of hinge loss function (hinge loss) and the triplet loss function (triplet loss) to improve the cross entropy loss. The improved cross entropy loss function is combined with the CNN model and LSTM network which are tested in the two classification problems. Then, the LSTM binary-optimize (LSTM-BO) model and CNN binary-optimize (CNN-BO) model are proposed, which are more effective in fitting the predicted errors and preventing overfitting. Finally, considering the characteristics of the processing text of the recurrent neural network, the influence of input words for the final classification is analysed, which can obtain the importance of each word to the classification results. The experiment results show that within the same time, the proposed weight-recurrent neural network (W-RNN) model gives higher weight to words with stronger emotional tendency to reduce the loss of emotional information, which improves the accuracy of classification.

中文翻译:

基于改进交叉熵和权重的跨域情感分类深度学习结构

在情感分类领域,卷积神经网络(CNN)和长短期记忆(LSTM)的分类和预测性能受到称赞,但其准确率、损失率和时间并不理想。为此,提出了一种结合改进的交叉熵和词权重的深度学习结构来解决跨域情感分类,其重点是通过优化和改进循环神经网络 (RNN) 和 CNN 来实现更好的文本情感分类。首先,我们利用铰链损失函数(hinge loss)和三重损失函数(triplet loss)的思想来改善交叉熵损失。改进的交叉熵损失函数结合CNN模型和LSTM网络在两个分类问题中进行了测试。然后,提出了LSTM二元优化(LSTM-BO)模型和CNN二元优化(CNN-BO)模型,它们在拟合预测误差和防止过拟合方面更有效。最后,结合循环神经网络处理文本的特点,分析输入词对最终分类的影响,可以得到每个词对分类结果的重要性。实验结果表明,在同一时间内,提出的权重递归神经网络(W-RNN)模型对情感倾向较强的词赋予更高的权重,减少情感信息的丢失,提高了分类的准确性。考虑到循环神经网络处理文本的特点,分析输入词对最终分类的影响,可以得到每个词对分类结果的重要性。实验结果表明,在同一时间内,提出的权重递归神经网络(W-RNN)模型对情感倾向较强的词赋予更高的权重,减少情感信息的丢失,提高了分类的准确性。考虑到循环神经网络处理文本的特点,分析输入词对最终分类的影响,可以得到每个词对分类结果的重要性。实验结果表明,在同一时间内,提出的权重递归神经网络(W-RNN)模型对情感倾向较强的词赋予更高的权重,减少情感信息的丢失,提高了分类的准确性。
更新日期:2020-06-29
down
wechat
bug