Multi-triad joint extraction method based on knowledge graph embedding

Abstract

The invention discloses a multi-triad joint extraction method based on knowledge graph embedding, comprising the following steps of: processing an acquired text statement to obtain a text statement matrix; inputting the text statement matrix into a Transformer model to extract semantic information of text statements to obtain semantic feature vectors; applying the semantic feature vectors to an entity recognition sequence labeling task to obtain entity recognition cross entropy loss loss1; applying the semantic feature vector to a relationship classification task, and solving entity recognition cross entropy loss loss2 of relationship classification; constructing an entity word relationship by utilizing an entity labeling prediction matrix and a statement entity word relationship classification matrix, and solving cross entropy loss loss3 of the relationship; calculating a minimized total loss function loss by utilizing an optimization algorithm based on gradient descent of the loss1,the loss2 and the loss3; and obtaining a trained Transformer model according to the text statement to be predicted, inputting the text statement to be predicted into the trained Transformer model to obtain a predicted semantic feature vector of the predicted text statement, and completing a multi-triad joint extraction method.

Description

technical field [0001] The invention relates to the technical field of data storage and processing, in particular to a triple extraction method in a knowledge map. Background technique [0002] The knowledge graph describes the concepts, entities and their relationships in the objective world in a structured form, expresses the information of the Internet in a form closer to the human cognitive world, and provides a way to better organize, manage and understand the massive information on the Internet. Capabilities, the knowledge graph mainly includes entities, relationships, and triples, and each triple represents a piece of knowledge. When there is a certain relationship between two entities, use (h, r, t) to represent a triplet, where h, t represent the head entity and tail entity respectively, and r represents the relationship, for example (China, capital, Beijing ) means the knowledge that "Beijing is the capital of China". [0003] Entity relationship learning is to a...

AI Technical Summary

Problems solved by technology

[0007] The present invention provides a multi-triple joint extraction method based on knowledge map embedding. The model training stage introduces knowledge map embedding under knowledge representation learning, so as to take into account the reasoning interaction between different relationships and extract multiple triples in one step. group, and solve the extraction challenges caused by entity sharing

Images