Looking for breakthrough ideas for innovation challenges? Try Patsnap Eureka!

Multi-triad joint extraction method based on knowledge graph embedding

A knowledge graph and triplet technology, applied in the field of data storage and processing

Active Publication Date: 2020-07-24
ZHEJIANG UNIV
View PDF3 Cites 42 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

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

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 more

Image

Smart Image Click on the blue labels to locate them in the text.
Viewing Examples
Smart Image
  • Multi-triad joint extraction method based on knowledge graph embedding
  • Multi-triad joint extraction method based on knowledge graph embedding
  • Multi-triad joint extraction method based on knowledge graph embedding

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0085] In order to describe the present invention more specifically, the technical solutions of the present invention will be described in detail below in conjunction with the accompanying drawings and specific embodiments.

[0086] Such as figure 1 As shown, in the training process, for the sake of simplicity, the word embedding layer uses 5 dimensions, and the position embedding layer uses 3 dimensions, that is, V=5+3=8. In actual processing, a larger Dimensions, such as 200 dimensions. The number of Transformer layers N is set to 2, the number of attention heads h is set to 2, and the dimension H of a single attention head is set to 4, which satisfies the constraints of 4*2=8. The number of entity recognition labeling categories is set to 5, that is, there are five labeling results of B-PER, I-PER, B-LOC, I-LOC and O. The number of relationship classifications is set to 5, that is, there are five relationships: provincial capital, location, tourist attraction, nationality...

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

No PUM Login to View More

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...

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
no application Login to View More
IPC IPC(8): G06F16/31G06F16/36G06F40/30G06N3/04
CPCG06F16/313G06F16/367G06N3/045
Inventor 陈华钧余海阳邓淑敏张宁豫
Owner ZHEJIANG UNIV
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Patsnap Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Patsnap Eureka Blog
Learn More
PatSnap group products