Knowledge graph pre-training method based on structured context information

Abstract

The invention discloses a knowledge map pre-training method based on structured context information, which includes: constructing an instance composed of context triples for the target triples, and using a triple integration module to analyze each context triple of the instance Groups are encoded to obtain integrated vectors; the integrated vectors of all context triples for the instance are composed of context vector sequences, and the structured information module is used to encode the context vector sequences to obtain the structural representation vectors of triples; the general task module is used to The structure representation vector of the triplet is calculated to obtain the predicted value of the label of the triplet, and the structural representation vector of the triplet is updated based on the cross-entropy loss between the predicted value of the label of the triplet and the true value of the label until the end of the training. Get the optimized structure representation vector of the target triplet. The structured representation vectors of triples obtained by this method incorporate contextual information.

Description

technical field [0001] The invention belongs to the technical field of data storage and processing, and in particular relates to a knowledge graph pre-training method based on structured context information. Background technique [0002] The Knowledge Graph can be regarded as a directed labeled graph, and the facts in the graph are represented as triples in the form of (head entity, relationship, tail entity), which are abbreviated as (h, r, t ). In recent years, knowledge graphs have developed rapidly in terms of construction and application, and have broad application prospects in artificial intelligence fields such as semantic search, information extraction, and question answering. [0003] Since the graph structure in knowledge graph contains a large amount of valuable information, it is crucial to extract deep structural information for various knowledge graph tasks, such as entity typing, link prediction, entity alignment, etc. The representation learning method embe...

AI Technical Summary

Problems solved by technology

Therefore, the main challenges of adapting pre-training KG representation learning models for different tasks are: (1) Regardless of the specific KG downstream tasks, the pre-trained model should be able to automatically capture the deep structural contextual information of a given triple; (2) The representation of entities and relationships needs to be trained in different ways according to different downstream tasks and different structural features of the input data of downstream tasks to improve its robustness

Images