【摘要】 当前大多数实体关系抽取方法无法获取较长句子中的远距离依赖信息,并且由于远程监督数据噪声的干扰导致关系抽取性能下降。因此本文提出一种基于双向长短期记忆网络(BiLSTM)和残差卷积神经网络(ResCNN)的实体关系抽取模型,该模型在向量表示阶段采用BiLSTM获取词语的上下文信息向量,利用残差网络将卷积神经网络中低层的特征传递到高层,有效解决梯度消失问题。同时将挤压-激励块嵌入残差网络中,能大幅降低数据噪声,强化特征传递,在池化阶段采用分段最大化池化方法来捕捉实体对的结构信息。设计在NYT-Freebase数据集上的验证实验,实验结果表明,该模型能够充分学习特征,显著提升实体关系抽取的效果。更多还原

【Abstract】 Most of relationship extraction methods cannot obtain long-distance dependent information from long sentences, and the performance of relationship extraction is degraded due to the data noise. This paper proposes a new relationship extraction model based on BiLSTM and ResCNN to solve these problems. The model uses BiLSTM to obtain the context information vector of words. The features of the middle or low layer in the convolutional neural network are transferred to the high layer through residual network, which effectively solves the problem of vanishing gradient. At the same time, embedding the squeeze-and-excitation block into the residual network can greatly reduce the data noise and strengthen the feature transfer. The piecewise max pooling method is used to capture the structural information of the entity pair. This paper designs verification experiments on NYT-Freebase dataset. Experimental results show that this model can fully learn features and significantly improve the effect of relationship extraction.更多还原