Entity linking method and device

Abstract

The invention provides an entity linking method and device.The entity linking method comprises the steps that a to-be-linked text is input into a pre-trained information labeling model, a first coding vector output by the information labeling model is obtained, the first coding vector represents an entity reference of the to-be-linked text, and the first coding vector represents the entity reference of the to-be-linked text; based on the first coding vector and time information contained in the to-be-linked text, resume information related to the to-be-linked text is screened out from a pre-constructed knowledge graph, the resume information is input into a pre-trained vector coding model, a second coding vector output by the vector coding model is obtained, and the second coding vector is used for coding the to-be-linked text. The first coding vector represents a candidate entity of the resume information, the second coding vector represents a candidate entity of the resume information, and entity linking is performed on the entity reference and the candidate entity under the condition that the matching degree between the first coding vector and the second coding vector is determined to be greater than a preset matching degree threshold value.

Description

technical field [0001] The present application relates to the technical field of knowledge graphs, in particular to an entity linking method and device, a computing device, and a computer-readable storage medium. Background technique [0002] With the rapid development of the Internet, all kinds of text information on the Internet include various entity designations such as names of people, places, and organizations. Due to the diversity of natural language expressions, an entity reference can often point to multiple real entities. Therefore, in order to correctly understand the real meaning of the entity reference in the text, it is necessary to link the entity reference in the text to the corresponding unambiguous entity knowledge base. Physically. [0003] Due to the excellent characteristics of end-to-end and no need for artificial feature engineering, neural network and deep learning methods have been quickly applied to some tasks of computer vision and natural languag...

AI Technical Summary

Problems solved by technology

The field of entity linking is no exception. Through methods such as shallow word vectors or neural network models, the effect of entity linking tasks has been improved to a certain extent, but at least there are problems such as low efficiency, limited applicability, and low accuracy that need to be resolved urgently.

Images