尽管已有利用lncRNA和蛋白质的信息来预测lncRPI的方法,但仅利用蛋白质和RNA的序列特征来进行预测相互作用仍然是一个挑战,并且模型预测的准确性有待提高。因此,本文提出了一种融合卷积神经网路和自注意力机制的预测模型LPI-Attention(L...尽管已有利用lncRNA和蛋白质的信息来预测lncRPI的方法,但仅利用蛋白质和RNA的序列特征来进行预测相互作用仍然是一个挑战,并且模型预测的准确性有待提高。因此,本文提出了一种融合卷积神经网路和自注意力机制的预测模型LPI-Attention(Long non-coding RNA based on self-attention mechanism),该模型采用了k-mer方法来编码RNA和蛋白质序列特征作为模型的输入,这种方法可以同时考虑两种序列的信息,从而提高了预测的准确性。此外,在密集型卷积模块中,使用两种尺度的特征提取,更好地捕捉局部和全局的信息。最后,将得到的特征输入自注意力循环网络层中,更好地处理序列数据的长期依赖关系,将得到的RNA、蛋白质二者特征信息融合成新的特征放入全连接层进行预测。实验结果表明,该模型不仅扩展了生物特征预测领域,而且可以学习RNA序列与蛋白质序列之间更多的相互作用关系,在预测RPIs方面表现优于大多数同类方法,在数据集RPIs1446、RPIs1807、RPIs488上的准确率分别达到91.7%、96.6%、91.6%。展开更多
目前大多数方面级情感分类研究都忽略了方面词的建模,以及方面词与上下文之间的交互信息,并且难以体现语法上与方面词有直接联系上下文单词的重要程度。针对上述问题,提出基于方面词交互(aspect word interaction,AWI)和图卷积网络(grap...目前大多数方面级情感分类研究都忽略了方面词的建模,以及方面词与上下文之间的交互信息,并且难以体现语法上与方面词有直接联系上下文单词的重要程度。针对上述问题,提出基于方面词交互(aspect word interaction,AWI)和图卷积网络(graph convolutional network,GCN)的方面级情感分类模型(AWI-GCN)。使用双向长短期记忆网络(bi-directional long short-term memory,Bi-LSTM)分别提取方面词和上下文的特征;采用GCN根据句法依存树进一步提取与方面词有直接语法联系的上下文情感特征;利用注意力机制学习方面词与上下文的交互信息,同时提取上下文中为方面词情感分类做出重要贡献的情感特征。针对3个公开数据集上的仿真实验结果表明,AWI-GCN模型相比当前代表模型取得了更好的情感分类效果。展开更多
Online advertising click-through rate(CTR) prediction is aimed at predicting the probability of a user clicking an ad,and it has undergone considerable development in recent years.One of the hot topics in this area is...Online advertising click-through rate(CTR) prediction is aimed at predicting the probability of a user clicking an ad,and it has undergone considerable development in recent years.One of the hot topics in this area is the construction of feature interactions to facilitate accurate prediction.Factorization machine provides second-order feature interactions by linearly multiplying hidden feature factors.However,real-world data present a complex and nonlinear structure.Hence,second-order feature interactions are unable to represent cross information adequately.This drawback has been addressed using deep neural networks(DNNs),which enable high-order nonlinear feature interactions.However,DNN-based feature interactions cannot easily optimize deep structures because of the absence of cross information in the original features.In this study,we propose an effective CTR prediction algorithm called CAN,which explicitly exploits the benefits of attention mechanisms and DNN models.The attention mechanism is used to provide rich and expressive low-order feature interactions and facilitate the optimization of DNN-based predictors that implicitly incorporate high-order nonlinear feature interactions.The experiments using two real datasets demonstrate that our proposed CAN model performs better than other cross feature-and DNN-based predictors.展开更多
文摘尽管已有利用lncRNA和蛋白质的信息来预测lncRPI的方法,但仅利用蛋白质和RNA的序列特征来进行预测相互作用仍然是一个挑战,并且模型预测的准确性有待提高。因此,本文提出了一种融合卷积神经网路和自注意力机制的预测模型LPI-Attention(Long non-coding RNA based on self-attention mechanism),该模型采用了k-mer方法来编码RNA和蛋白质序列特征作为模型的输入,这种方法可以同时考虑两种序列的信息,从而提高了预测的准确性。此外,在密集型卷积模块中,使用两种尺度的特征提取,更好地捕捉局部和全局的信息。最后,将得到的特征输入自注意力循环网络层中,更好地处理序列数据的长期依赖关系,将得到的RNA、蛋白质二者特征信息融合成新的特征放入全连接层进行预测。实验结果表明,该模型不仅扩展了生物特征预测领域,而且可以学习RNA序列与蛋白质序列之间更多的相互作用关系,在预测RPIs方面表现优于大多数同类方法,在数据集RPIs1446、RPIs1807、RPIs488上的准确率分别达到91.7%、96.6%、91.6%。
文摘目前大多数方面级情感分类研究都忽略了方面词的建模,以及方面词与上下文之间的交互信息,并且难以体现语法上与方面词有直接联系上下文单词的重要程度。针对上述问题,提出基于方面词交互(aspect word interaction,AWI)和图卷积网络(graph convolutional network,GCN)的方面级情感分类模型(AWI-GCN)。使用双向长短期记忆网络(bi-directional long short-term memory,Bi-LSTM)分别提取方面词和上下文的特征;采用GCN根据句法依存树进一步提取与方面词有直接语法联系的上下文情感特征;利用注意力机制学习方面词与上下文的交互信息,同时提取上下文中为方面词情感分类做出重要贡献的情感特征。针对3个公开数据集上的仿真实验结果表明,AWI-GCN模型相比当前代表模型取得了更好的情感分类效果。
文摘Online advertising click-through rate(CTR) prediction is aimed at predicting the probability of a user clicking an ad,and it has undergone considerable development in recent years.One of the hot topics in this area is the construction of feature interactions to facilitate accurate prediction.Factorization machine provides second-order feature interactions by linearly multiplying hidden feature factors.However,real-world data present a complex and nonlinear structure.Hence,second-order feature interactions are unable to represent cross information adequately.This drawback has been addressed using deep neural networks(DNNs),which enable high-order nonlinear feature interactions.However,DNN-based feature interactions cannot easily optimize deep structures because of the absence of cross information in the original features.In this study,we propose an effective CTR prediction algorithm called CAN,which explicitly exploits the benefits of attention mechanisms and DNN models.The attention mechanism is used to provide rich and expressive low-order feature interactions and facilitate the optimization of DNN-based predictors that implicitly incorporate high-order nonlinear feature interactions.The experiments using two real datasets demonstrate that our proposed CAN model performs better than other cross feature-and DNN-based predictors.
