Sample knowledge graph relationship learning method and system based on adversarial attention mechanism

Abstract

The invention discloses a sample knowledge graph relation learning method and system based on an adversarial attention mechanism. The method comprises: obtaining relation triples in a target knowledgegraph and natural text description corresponding to the relation triples; performing representation learning on the target knowledge graph to obtain vector representation of a triple; performing linedrawing representation learning on the text corresponding to the triple to obtain word vector representation in the text; constructing a conditional adversarial generation network with a denoising attention module and a confusion attention module; and performing optimization training on the conditional adversarial generation network, and predicting a target entity corresponding to the relationship query without the relationship type ru based on the trained conditional adversarial generation network. The relationship category of traditional relationship prediction is expanded from a visible relationship to an unseen relationship category, so that the range of predicting the relationship category is enlarged. And the scale of the training data is reduced from the traditional big data scaleto the learning and prediction of the unseen relationship by only needing a small number of samples or even one sample.

Description

technical field [0001] The present invention relates to the technical field of knowledge graph-oriented relation extraction, in particular to a method and system for learning a sample knowledge graph relation based on an adversarial attention mechanism. Background technique [0002] The statements in this section merely provide background information related to the present invention and do not necessarily constitute prior art. [0003] Large-scale knowledge graphs represent fragmented knowledge as binary relationships between entities, usually in the form of triples: (subject, predicate, object). This structured knowledge plays an important supporting role in many downstream applications, such as automatic question answering, recommendation system, semantic web search and other tasks. However, although the current knowledge graphs are large in scale, these knowledge graphs are far from perfect enough to meet the growing demands of intelligent systems. In order to realize t...

AI Technical Summary

Problems solved by technology

At present, methods based on few samples or zero samples are mostly concentrated in the field of image and imitation, and few of them are applied to the field of relation extraction in knowledge graphs.

At the same time, most of the existing methods need to construct domain information, and it is difficult to realize automatic knowledge sharing and inductive transfer between categories.

Images