Medical entity relation joint extraction method

An entity relationship, medical technology, applied in the field of joint extraction of medical entity relationship, can solve the problem of not being able to identify well

Active Publication Date: 2021-05-18
NORTHEASTERN UNIV
View PDF4 Cites 9 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

Meanwhile, existing methods cannot well identify fact triples of various overlapping relation types

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
  • Medical entity relation joint extraction method
  • Medical entity relation joint extraction method
  • Medical entity relation joint extraction method

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0028] The specific implementation manners of the present invention will be clearly and completely described below in conjunction with the accompanying drawings.

[0029] In order to facilitate the understanding of the present application, the present application will be described more fully below with reference to the relevant drawings. Preferred embodiments of the application are shown in the accompanying drawings. However, the present application can be embodied in many different forms and is not limited to the embodiments described herein. On the contrary, the purpose of providing these embodiments is to make the disclosure of the application more thorough and comprehensive.

[0030] The medical entity relationship joint extraction method of this embodiment, such as figure 1 shown, including the following steps:

[0031] Step 1: Obtain the training instance and the Chinese pre-training model for the medical field; this step specifically includes the following two aspect...

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 medical entity relationship joint extraction method, and relates to an entity relationship extraction method. Comprising the following steps: creating a Chinese pre-training model ChineseMedBert oriented to the medical field, and obtaining a training instance; performing fine adjustment on the ChineseMedBert by utilizing the training instance, and obtaining word vector representation of a given medical text through the ChineseMedBert; obtaining feature vector representation of the text according to the word vector representation of the text; obtaining enhanced semantic vector representation of the text; using the enhanced semantic vector representation of the text to predict a tag sequence of a given medical text; and according to the predicted label sequence, extracting a relation triple of the text. The problem of error accumulation of a traditional assembly line method is relieved, the problem that a joint extraction method based on parameter sharing neglects sub-task interaction information and the common overlapping relation problem in medical texts are solved, fact triple information of various overlapping relation types can be effectively extracted, and the accuracy of medical entity relation extraction is improved.

Description

technical field [0001] The invention relates to an entity relationship extraction method, in particular to a medical entity relationship joint extraction method. Background technique [0002] Nowadays, knowledge graphs have been applied to all walks of life, and have also been extensively researched and applied in the medical field. Among them, the medical knowledge extraction task is the key to constructing a medical knowledge graph. Medical knowledge extraction refers to the extraction of medical fact triples from semi-structured or unstructured raw data such as clinical data, medical literature, and medical books using manual or automated methods. For example, in the sentence "acute laryngitis in children is easy to be combined with acute laryngitis and respiratory infection in children", (acute laryngitis in children, complications, acute laryngitis in children and respiratory infection) constitutes a medical fact triplet, among which, " "Pediatric acute laryngitis" an...

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): G06F40/279G06F40/284G06N3/04G06N3/08
CPCG06F40/279G06F40/284G06N3/049G06N3/08
Inventor 杨晓春郑婷月李雨繁王斌
Owner NORTHEASTERN UNIV
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