基于多通道卷积神经网络的中文文本关系抽取

Chinese text relation extraction based on a multi-channel convolutional neural network

给出了一种多通道卷积神经网络(Convolutional Neural Network,CNN)方法实现中文文本端到端的关系抽取.每个通道用分层的网络结构,在传播过程中互不影响,使神经网络能学习到不同的表示.结合中文语言的难点,加入注意力机制(Attention Mechanism,Att)获取更多的语义特征,并通过分段平均池化融入句子的结构信息.经过最大池化层获得句子的最终表示后,计算关系得分,并用排序损失函数(Ranking-Loss Function,RL)代替交叉熵函数进行训练.实验结果表明,提出的MCNN_Att_RL(Multi CNN_Att_RL)模型能有效提高关系抽取的查准率、召回率和F_(1)值.

This paper presents an end-to-end method for Chinese text relation extraction based on a multichannel CNN(convolutional neural network).Each channel is stacked with a layered neural network;these channels do not interact during recurrent propagation,which enables a neural network to learn different representations.Considering the nuances of the Chinese language,we employed the attention mechanism to extract the semantic features of a sentence,and then integrate structural information using piecewise average pooling.After the maximum pooling layer,the final representation of the sentence is obtained and a relational score is calculated.Finally,the ranking-loss function is used to replace the cross-entropy function for training.The experimental results show that the MCNN_Att_RL(Multi CNN_Att_RL)model proposed in this paper can effectively improve the precision,recall,and F_(1)value of entity relation extraction.