Unlock instant, AI-driven research and patent intelligence for your innovation.

Relationship extraction system, method and device

A technology of relationship extraction and relationship, applied in the field of information extraction, can solve the problems of inability to learn linguistic features, limited corpus size, inability to effectively remove noise, etc., and achieve the effect of improving performance

Inactive Publication Date: 2020-12-25
POTEVIO INFORMATION TECH CO LTD
View PDF0 Cites 4 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0005] However, this method is limited by the size of the corpus and cannot learn more linguistic features
At the same time, only using the attention mechanism cannot effectively remove the noise in the input sentence, which affects the final classification accuracy.

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
  • Relationship extraction system, method and device
  • Relationship extraction system, method and device
  • Relationship extraction system, method and device

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0041] In order to make the object, technical solution and advantages of the present invention clearer, the present invention will be further described in detail below in conjunction with the accompanying drawings.

[0042] For the sake of brevity and intuition in description, the solution of the present invention is described below by describing several representative implementation manners. Numerous details in the embodiments are only used to help the understanding of the solutions of the present invention. But obviously, the technical solutions of the present invention may not be limited to these details when implemented. In order to avoid unnecessarily obscuring the solution of the present invention, some embodiments are not described in detail, but only a framework is given. Hereinafter, "including" means "including but not limited to", and "according to..." means "at least according to, but not limited to only based on...". Due to the language habits of Chinese, when t...

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 embodiment of the invention provides a relation extraction system, method and device. The system comprises: a BERT layer used for classifying vector matrixes of input sentences, and classified categories include entity-unrelated noise sentences and entity-related sentences; the convolutional neural network (CNN) layer that is used for converting a vector matrix of sentences classified as entities having relationships into sentence vectors; the attention layer that is used for calculating the similarity between the sentence vector and the relationship vector, setting a weight for the sentence vector based on the similarity, and obtaining an output matrix of the relationship vector based on a weighted summation result of the sentence vector; the linear layer that is used for carrying outdimension reduction on the output matrix to obtain an output vector; and the Softmax layer that is used for executing probability planning calculation on the output vector to obtain relationship probability distribution of the input sentence.

Description

technical field [0001] The invention belongs to the technical field of information extraction, in particular to a relation extraction system, method and device. Background technique [0002] Information extraction aims to extract structured information from large-scale unstructured or semi-structured natural language texts. Relation extraction is one of the important sub-tasks, the main purpose is to identify entities from text and extract the semantic relationship between entities. Relational extraction refers to the task of judging the relationship between two entities given two entities and the sentences in which they are located. For example, the sentence "Bill Gates is the founder of Microsoft Corporation" contains an entity pair (Bill Gates, Microsoft Corporation), and the relationship between these two entities is "founder". [0003] Deep learning is one of the hot spots in machine learning research. Its main idea is to simulate the human brain neural network to est...

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
Patent Type & Authority Applications(China)
IPC IPC(8): G06F40/295G06F40/30G06K9/62G06N3/04G06N3/08
CPCG06N3/08G06N3/045G06F18/241
Inventor 张鹏
Owner POTEVIO INFORMATION TECH CO LTD