A Knowledge Graph Composite Representation Learning Method Combining Rules and Paths
A technology of knowledge graph and learning method, applied in the fields of unstructured text data retrieval, instrumentation, calculation, etc., can solve the problems of limiting the accuracy of relationship path representation, not considering the combination of relationships, etc., to achieve good practicability and improve efficiency performance, improve accuracy
Active Publication Date: 2021-01-05
BEIHANG UNIV
View PDF3 Cites 0 Cited by
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
However, this method directly combines the vector representation of the relationship in the semantic combination operation of the relationship path, without considering that the combination of the relationship itself should be a semantic level operation, which limits the accuracy of the relationship path representation
Method used
the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
View moreImage
Smart Image Click on the blue labels to locate them in the text.
Smart ImageViewing Examples
Examples
Experimental program
Comparison scheme
Effect test
Embodiment Construction
[0040] The following will clearly and completely describe the technical solutions in the embodiments of the present invention with reference to the accompanying drawings in the embodiments of the present invention. Obviously, the described embodiments are only some, not all, embodiments of the present invention. Based on the embodiments of the present invention, all other embodiments obtained by persons of ordinary skill in the art without making creative efforts belong to the protection scope of the present invention.
[0041] The embodiment of the present invention discloses a knowledge map combination representation learning method combining rules and paths, which not only improves the accuracy of relation representation, but also uses rules to establish semantic associations between relations, and vectors of relations with semantic associations Constrain the representation, add more semantic information in the vector representation of the relationship, and improve the accur...
the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More PUM
Login to View More Abstract
The invention discloses a knowledge map combination representation learning method combining rules and paths. First, logical rules are extracted from the knowledge map, and the logical rules are coded and represented; then, based on the coded and represented rules, the semantic combination of relations in the relational path is completed. Operate and establish the semantic association between relation pairs; finally combine the triplet, the vector representation of the relational path between entities and the semantic relational constraints between relational vectors to jointly construct the energy equation and obtain the minimized evaluation function. The invention discloses a knowledge map combination representation learning method combining rules and paths, which not only improves the accuracy of relation representation, but also uses rules to establish semantic associations between relations, and performs vector representation of relations with semantic associations. Constraints, adding more semantic information in the vector representation of the relationship, improving the accuracy of the vector representation of the relationship.
Description
technical field [0001] The present invention relates to the technical fields of natural language processing and knowledge graph, and more specifically relates to a knowledge graph combination representation learning method combining rules and paths. Background technique [0002] In recent years, with the rapid development of Internet technology and application models, the explosive growth of data has been triggered, which contains a lot of valuable knowledge; the knowledge map describes various concepts, entities and their relationships in a structured form, and integrates massive Information is expressed in a form that is closer to the human cognitive world. At present, knowledge graph has played an important role in semantic search, intelligent question answering system, data mining and other fields. [0003] The knowledge graph describes the massive and valuable knowledge in the database through the triple knowledge representation of (head entity, relationship, tail enti...
Claims
the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More Application Information
Patent Timeline
Login to View More Patent Type & Authority Patents(China)
IPC IPC(8): G06F16/36G06F40/279
CPCG06F16/367G06F40/279
Inventor 牛广林李波张永飞李晶阳
Owner BEIHANG UNIV