Entity relationship joint extraction method, device, computer terminal and storage medium

A technology of entity relationship and relationship, applied in the direction of calculation, instrument, biological neural network model, etc., can solve the problems of large amount of calculation, improvement of accuracy rate of triplet extraction, and inability to fully integrate, so as to improve accuracy rate and avoid wrong transmission and redundant entities, improving the effect of features

Active Publication Date: 2022-06-28
CHENGDU SHULIANYUNSUAN TECH CORP
View PDF0 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

However, using a one-dimensional vector to represent the feature information of each text requires a huge amount of calculation and cannot fully integrate the features of the two sub-tasks of entity recognition and relationship extraction, so that the accuracy of triplet extraction is limited.

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, device, computer terminal and storage medium
  • Entity relationship joint extraction method, device, computer terminal and storage medium
  • Entity relationship joint extraction method, device, computer terminal and storage medium

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0057] figure 1 It is a schematic flowchart of the entity relationship joint extraction method of the present embodiment, and the method includes the following steps:

[0058] In step S100, a text tensor is obtained based on the text data.

[0059] In this embodiment, the text data of "Zhang San was born in Chengdu." is used as an example for description. After the above text is input, the text data will be cleaned first, and the unnecessary text data will be deleted. Based on each character, the A feature vector representing the character to be processed can be obtained. According to the number of extracted features, the dimension of the vector is also different.

[0060] After inputting the text feature model, a text tensor can be obtained. For example, using bert-base-chinese to extract the input text feature, a 768-dimensional feature vector can be extracted. The above 9 characters (including the period) are spliced ​​in order. These vectors, then is a 9*768 tensor matri...

Embodiment 2

[0092] The present application also provides an entity relationship joint extraction device, such as Figure 5 shown, including:

[0093] a pre-extraction module 10 for obtaining text tensors based on text data;

[0094] The segmentation module 20 is used to obtain the head feature tensor and the tail feature tensor of the text according to the text tensor;

[0095] A fusion module 30, configured to perform feature fusion on the head feature tensor and the transposed tail feature tensor to obtain a fusion tensor;

[0096] A scoring module 40 is used to input the fusion tensor into a convolutional neural network to obtain a scoring tensor;

[0097] The extraction module 50 is configured to input the scoring tensor into the prediction model, obtain the probability distribution data of each element in the scoring tensor in the entity and relation label space, and output the extraction result according to the probability distribution data.

[0098] The present application furth...

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 discloses a method, a device, a computer terminal and a storage medium for joint extraction of entity relations. The entity-relationship joint extraction method includes: obtaining a text tensor based on text data; obtaining a head feature tensor and a tail feature tensor of the text according to the text tensor; combining the head feature tensor with the transposed The tail feature tensor is subjected to feature fusion to obtain a fusion tensor; the fusion tensor is input into a convolutional neural network to obtain a scoring tensor; the scoring tensor is input into a prediction model to obtain the scores of each element in the scoring tensor The probability distribution data of the label space of the entity and the relationship, and output the extraction result according to the probability distribution data. In natural language processing, the convolutional neural network is used to further extract features on the two-dimensional matrix, and the joint extraction of subject, object, and relationship is realized, which can not only greatly reduce the amount of calculation, but also improve the accuracy of triplet extraction.

Description

technical field [0001] The present invention relates to the field of natural language processing, in particular to a method, device, computer terminal and storage medium for joint extraction of entity relationships. Background technique [0002] There are two most commonly used entity and relationship extraction methods, one is the pipeline extraction method represented by the pipeline, and the other is the entity-relationship extraction method. The pipeline extraction method believes that entities and relationships belong to different semantic spaces, and the extraction of entities and relationships needs to be divided into two tasks, namely named entity recognition and relationship classification. This extraction method has problems such as wrong transmission and redundant entities. The entity-relationship joint extraction method believes that entities and relationships belong to the same semantic space, and it is necessary to fully integrate entity features and relationsh...

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 Patents(China)
IPC IPC(8): G06F40/279G06N3/04
Inventor 不公告发明人
Owner CHENGDU SHULIANYUNSUAN TECH CORP
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