Method and device for determining relationship between two entities in text statement and electronic equipment

Abstract

The embodiment of the invention provides a method and device for determining the relationship between two entities in a text statement and electronic equipment. The method comprises the steps: determining the text statement to be tested and position information; inputting the to-be-tested text statement and the position information into an entity relationship extraction model, and outputting a relationship type of the two entities corresponding to the to-be-tested text statement and the position information, wherein the entity relationship extraction model is obtained by training based on a sample text statement, position information and two predetermined entity relationship type tags corresponding to the sample text statement and the position information; and when the entity relationshipextraction model is trained, sample text statements and position information are processed by adopting a time attenuation attention mechanism, and the sample text statements and the position information are automatically expanded by a standard manual annotation library through a remote supervision mechanism. According to the method, the device and the electronic equipment provided by the embodiment of the invention, depth information is considered when the human body action recognition result is evaluated, and the method is more suitable for evaluating human body action capture.

Description

technical field [0001] The present invention relates to the technical field of knowledge graph entity-to-relationships, and in particular to a method, device and electronic device for determining the relationship between two entities in a text sentence. Background technique [0002] With the rapid development of technology, the amount of information available to humans is increasing exponentially. Today's network contains a large amount of unstructured or semi-structured information. It is important to mine the information required by practical application scenarios from huge amounts of data. At present, the research direction in the field of big data is hot. It is a challenging problem to use technical means to automatically summarize, classify, and extract massive unstructured data to form structured knowledge and store it. Research on Information Extraction has also emerged. Information extraction extracts unstructured information in text data to form structured knowledg...

AI Technical Summary

Problems solved by technology

[0005] The embodiment of the present invention provides a method, device and electronic device for determining the relationship between two entities in a text sentence, which are used to solve the training of the entity relationship extraction model that includes a large number of mislabeled and noise sample libraries expanded by the remote supervision mechanism in the prior art The low accuracy of the trained entity relationship extraction model caused by the samples, and the low accuracy of the trained entity relationship extraction model when it is used to extract entity relationships

Images