Entity relationship extracting system based on deep neural network

Abstract

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.

Description

technical field

[0001] The invention relates to the field of natural language processing, in particular to an entity relationship extraction system based on a deep neural network. Background technique

[0002] With the rapid development of the Internet, the Internet has become the main channel for people to obtain information, and the content of text data on the Internet is also showing an exponential growth trend. The text data on the Internet contains a wealth of information, which is very useful for us to build knowledge bases or knowledge graphs; however, the workload of manual knowledge extraction is extremely huge. If computers can understand and extract useful information, it will be very important. meaning. However, almost all text data on the Internet exists in the form of natural language, which is unstructured and cannot be directly processed by computers. In order to solve this problem, information extraction technology emerges as the times require. Information...

Images