Entity relationship extracting system based on deep neural network

The invention relates to the field of natural language processing, in particular to an entity relationship extracting system based on a deep neural network. Texts to be processed are input into the system, and the system achieves automatic entity relationship judgement and output; the system inputs word property incorporating characteristics into a convolutional neural network, wherein the convolutional neural network completes automatic characteristic extraction of information of words, word properties and entity positions with respect to extracting relationship and performs automatic classification of the entity relationship. Manual characteristic extraction is not needed, and the prediction efficiency and accuracy are higher. The system provides an automatic entity relationship extracting tool. 本发明涉及自然语言处理领域，特别涉及基于深度神经网络的实体关系抽取系统；将待处理文本输入所述系统中，所述系统实现实体关系的自动判断和输出；所述系统将词性纳入特征信息输入到卷积神经网络中，由卷积神经网络来完成对包括词、词性和相对于待抽取关系的实体位置的信息的自动特征提取，进行实体关系的自动分类；无需手动进行特征提取，预测的效率和准确率更高。所述系统提供实体关系的自动抽取工具。