Entity relationship joint extraction method and system

A technology of entity relationship and relationship extraction, applied in the direction of neural learning methods, instruments, biological neural network models, etc., can solve problems such as relationship overlap, achieve the effect of improving performance and solving relationship overlap

Active Publication Date: 2020-05-15
SOUTH CHINA UNIV OF TECH
View PDF4 Cites 36 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0005] The purpose of the present invention is to solve the problem of overlapping relationships in the prior art, and to provide a joint extraction method for entity relationships

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
  • Entity relationship joint extraction method and system
  • Entity relationship joint extraction method and system
  • Entity relationship joint extraction method and system

Examples

Experimental program
Comparison scheme
Effect test

Embodiment

[0039] Such as figure 1 Shown is a flow chart of an entity-relationship joint extraction method, the method includes steps:

[0040] (1) data preprocessing is carried out to input sentence, and described preprocessing comprises:

[0041] Label entities and relationships according to the BIO (Begin, Inside, Outside) labeling mechanism. Each entity contains one or more words, label each word, and obtain the start and end positions of each entity as well as the entity type.

[0042] In this embodiment, the entity tag sequence corresponding to the sentence "Smith lives in California." is "B-PER O O B-LOC". Where "PER" indicates a person's name, the label "O" indicates a non-entity, and "LOC" indicates a location. The relationship labels corresponding to this sentence are [['N', 'N', 'N', 'live in'], ['N', 'N', 'N', 'N'], ['N', 'N', 'N', 'N'], ['live in', 'N', 'N', 'N']]. The relationship between each two words is marked, 'N' means that there is no relationship, and 'live in' m...

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 an entity relationship joint extraction method. The method comprises the steps of performing data preprocessing on an input sentence; mapping each word in the input sentence into a corresponding word vector; inputting the obtained word vectors into an entity relationship joint extraction model based on a long and short-term memory network and a graph convolutional neural network for training; and adopting the trained LSTM-GCN model to carry out entity extraction and relationship extraction. According to the method, the sequence information and the region information ofthe input sentence can be captured at the same time through the LSTM and the GCN, each word can be better expressed, the performance of entity extraction and relationship extraction is improved, and the method has certain practicability.

Description

technical field [0001] The present invention relates to the technical field of application of deep learning algorithms, in particular to a method and system for entity-relationship joint extraction. Background technique [0002] With the rise of the digital age, there has been an explosion of information in the form of social media, articles, news, and more. Much of this data is in unstructured form, and manual management and effective use of this information is cumbersome, tedious, and time-consuming. Therefore, the information explosion and the demand for more complex and effective information processing tools have made people pay more and more attention to the technology of automatic information extraction. Information extraction systems take natural language text as input, identify relevant knowledge elements (usually of a predefined type) from the text, and generate structured information specified by specific standards, which are relevant to specific applications. In...

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): G06F40/211G06F40/295G06N3/04G06N3/08
CPCG06N3/084G06N3/044G06N3/045
Inventor 蔡毅陈峰
Owner SOUTH CHINA UNIV OF TECH
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Try Eureka
PatSnap group products

Browse by: Latest US Patents, China's latest patents, Technical Efficacy Thesaurus, Application Domain, Technology Topic.

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap