Joint knowledge embedded method based on cost sensitive learning

Abstract

The joint knowledge embedded method based on cost sensitive learning comprises the steps of S 1 establishing a training set consisting of a triple score function through a knowledge base, S 2 establishing a triple score function based on entities and relational embedded vectors, and establishing an optimization objective based on maximum margin under the condition of only considering context relation of the entity level. S 3 establishing cost sensitive joint embedded models. The joint knowledge embedded method based on the cost sensitive learning is characterized in that each entity and each relationship in the knowledge base and the knowledge mapping are respectively embedded into lower dimensional space on the basis of various related facts of the knowledge base. The layered contextual information of the knowledge base and the knowledge mapping is utilized better, making the embedded results satisfy the semantic structure of the knowledge base and the knowledge mapping better and enhancing predictive effects. The joint knowledge embedded method based on the cost sensitive learning has the advantages of expressing the visualization of the knowledge base and the knowledge mapping by utilizing the joint knowledge embedded method based on the cost sensitive learning, predicting the knowledge which is not within the knowledge base in answering question system.

Description

technical field [0001] The invention belongs to the technical field of knowledge graphs, and in particular relates to a joint knowledge embedding method based on cost-sensitive learning that simultaneously embeds entities and relationships in knowledge bases and knowledge graphs into low-dimensional spaces. Background technique [0002] In the era of big data, knowledge representation and reasoning in knowledge bases are critical and challenging tasks. Generally speaking, the basic composition of a knowledge base is a tuple unit with a name and a definite meaning, called an entity; and its semantic structure is expressed by a higher-order interaction unit between entities, called a relationship. As a powerful tool that is often used nowadays, knowledge embedding builds statistical models in low-dimensional space to quantitatively express and evaluate these units and the relationship between them. [0003] To learn effective embedding results, semantically similar units shou...

AI Technical Summary

Problems solved by technology

[0004] Most related work focuses on embedding at the entity level, while relationships are often not

Images