Enterprise entity relation extraction method based on convolutional neural network

Abstract

The invention discloses an enterprise entity relation extraction method based on a convolutional neural network. The method comprises the steps of a relation corpus building stage, wherein an initial seed relation pair set is built artificially, and by means of an internet search engine and a Bootstrapping technology, relation language materials are generated in an iteration mode, and finally a relation corpus is formed; a relation classification model training stage, wherein term vectors and position embedding are combined to build a sentence vector matrix representation to serve as input of a network, the convolutional neural network is built, the network is trained by means of a back propagation algorithm, and a relation classification model is obtained; an enterprise entity relation extraction stage in a web page, wherein the web page is preprocessed by combining web page text extraction with a named entity identification technology, and then enterprise entity relation extraction is conducted on the preprocessed web page. By means of the method, not only the defects of an artificial feature method can be overcome, but also the enterprise entity relation can be extracted from the web page more accurately and efficiently.

Description

technical field [0001] The invention relates to deep learning and natural language processing technology, in particular to a method for extracting entity relations based on volume and neural network. Background technique [0002] With the popularization and development of the Internet, the amount of information is growing exponentially. Hundreds of millions of text data are constantly updated on the Internet every day, including news, social networking, and government website data. These data contain a lot of valuable information for people, which plays a vital role in people's production and life. However, in the face of these massive Internet data, it is difficult to quickly obtain the information you need from it by manpower alone. In order to cope with the challenges brought by information overload, there is an urgent need for some automated methods to help people quickly find useful information. [0003] It is against this background that the research on entity relati...

AI Technical Summary

Problems solved by technology

The shortcomings of this method are also obvious. First, it needs to manually label the training data set, which is very time-consuming and labor-intensive; second, it relies on some natural language processing tools to extract features, and these tools often have a lot of errors, which will be in the relationship. Continuous propagation and amplification in the extraction system will eventually affect the effect of relationship extraction

Images