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

End-to-end entity relation joint extraction method and system based on relation decomposition

An entity relationship and relationship technology, applied in the field of deep learning and natural language processing, can solve the problems of overlapping entities and relationships, and achieve the effect of improving performance and good practicability

Pending Publication Date: 2022-05-31
YUNNAN UNIV
View PDF0 Cites 4 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

However, the traditional entity-relationship joint extraction scheme only considers the case of extracting a triplet in a sentence
But actually, if Figure 4 As shown, the sentences we extract often contain multiple triples, and these triples may also have overlapping entities and relations

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
  • End-to-end entity relation joint extraction method and system based on relation decomposition
  • End-to-end entity relation joint extraction method and system based on relation decomposition
  • End-to-end entity relation joint extraction method and system based on relation decomposition

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0037] All features disclosed in this specification, or steps in all methods or processes disclosed, may be combined in any manner, except for mutually exclusive features and / or steps.

[0038] Any feature disclosed in this specification (including any appended claims, abstract), unless otherwise stated, may be replaced by alternative features which are equivalent or serve a similar purpose. That is, unless expressly stated otherwise, each feature is one example only of a series of equivalent or similar features.

[0039] Such as figure 1 As shown, the present invention discloses an end-to-end entity-relationship joint extraction method based on relationship decomposition, including the following steps:

[0040] Data preprocessing: convert the sentence of the entity relationship to be extracted according to the format required by BERT, and convert it into a vector form, which is used as the input of the BERT model; at the same time, convert the triplet label into the form of...

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 end-to-end entity relationship joint extraction method based on relationship decomposition, which is characterized by comprising the following steps of: data preprocessing: converting triples of entities and relationships labeled in a training set into a vector form according to a dictionary in a BERT model; model training: carrying out relation classification according to text vectors output by the BERT model, and then fusing relation features with sentence features to carry out head and tail entity recognition: result decoding: decoding entity tags recognized under different relation categories, and combining the decoded entity tags with relations to obtain entity relation triples existing in sentences. According to the method, the sentence features under different relations are modeled, so that the extraction problem of the overlapped triples in the sentences can be effectively solved, the performance of entity relation joint extraction is improved, and the method has good practicability.

Description

technical field [0001] The present invention relates to deep learning and natural language processing technology, in particular to an end-to-end entity-relationship joint extraction method and system based on relationship decomposition. Background technique [0002] As an important part of information extraction, triple extraction is to obtain structured knowledge in the form of (head entity, relationship, tail entity) from a set of unstructured texts, also called entity relationship extraction. This is one of the key tasks in building a knowledge graph, and it is an important foundation for other related natural language processing tasks, such as: machine translation, text summarization, recommendation system, etc. [0003] Most of the early extraction methods used a pipeline-based method for entity relationship extraction. These methods regarded the extraction task as two independent subtasks, namely named entity recognition and relationship classification. This approach ...

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): G06F16/33G06F16/35G06F40/242G06F40/295G06N3/04G06N3/08
CPCG06F16/3344G06F16/35G06F40/242G06F40/295G06N3/084G06N3/048
Inventor 张璇高宸杜鲲鹏农琼马秋颖袁子豪
Owner YUNNAN 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

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

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap|About US| Contact US: help@patsnap.com