Small sample medical relationship classification method based on multilayer attention mechanism

A technology of relational classification and small samples, which is applied in text database clustering/classification, neural learning methods, healthcare informatics, etc., to achieve the effects of reducing impact, precise judgment, and improving model accuracy

Pending Publication Date: 2021-10-15
NORTHEASTERN UNIV
View PDF0 Cites 1 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0008] In the existing small-sample relational classification methods, in view of the noise problem that may occur in the support set, the existing method uses the attention m

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
  • Small sample medical relationship classification method based on multilayer attention mechanism
  • Small sample medical relationship classification method based on multilayer attention mechanism
  • Small sample medical relationship classification method based on multilayer attention mechanism

Examples

Experimental program
Comparison scheme
Effect test

Example Embodiment

[0048] In order to understand the present application, the present application will be further described with reference to the related drawings. The preferred embodiment of the present application is given in the drawings.

[0049] The core idea of ​​the present invention is to reduce the impact of noise sentences to the final category vector by imparting different weights to each sentence, specifically, using multi-layer care mechanisms to give important samples to higher The weight, the noise sample to lower weight, thereby increasing the accuracy of the relationship classification.

[0050] PrototyPical Networks is a relatively practical and representative approach to solving small sample classification problems. figure 1 It is a schematic diagram of the prototype network. The main idea of ​​prototype network is very simple: when there is n class in support, each class has K sentences, see the mean of sentence vectors corresponding to each class, will The N mean vector, as a re...

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 provides a small sample medical relationship classification method based on a multilayer attention mechanism, and relates to the technical field of relationship classification. The method comprises the steps: constructing a relation classification model based on a neural network, wherein the relation classification model comprises a word embedding layer, two position embedding layers, a coding layer and a full connection layer, sentences in a support set and a query set are input, and relation categories to which the sentences in the query set belong are output; obtaining a public relationship extraction data set, setting training times, training the relationship classification model by utilizing a training set of the relationship extraction data set, and randomly extracting a support set and a query set which are required for training the relationship classification model each time from the training set; for a support set containing any N relationships and a query set in which sentences contained in the support set belong to the N relationships, utilizing the trained relationship classification model to predict a relationship category in which the sentences in the query set belong to the support set. The influence of noise on the accuracy of the model is reduced from different aspects, and the relationship between entities is mined more accurately.

Description

technical field [0001] The invention relates to the technical field of relationship classification, in particular to a small-sample medical relationship classification method based on a multi-layer attention mechanism. Background technique [0002] Knowledge Graph is a method to state entities in the objective world and the relationship between different entities in a structured form. The knowledge graph consists of entity-relationship triples (e 1 ,r,e 2 ) form, where e 1 、e 2 Represents an entity, and r represents a relationship between two entities. Relation classification task is an important subtask of knowledge graph. Relation classification aims to extract relations from unstructured text on the basis of known two entities in entity-relation triples. In recent years, relationship classification has also been widely used in the medical field. Given an unstructured medical text, find out the relationship between two known medical entities based on the two known en...

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
IPC IPC(8): G06F16/35G06F16/36G06K9/62G06N3/04G06N3/08G16H40/00
CPCG06F16/35G06F16/367G16H40/00G06N3/08G06N3/045G06F18/2411G06F18/214Y02D10/00
Inventor 马连博张爽王兴伟黄敏
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