Eureka AIR delivers breakthrough ideas for toughest innovation challenges, trusted by R&D personnel around the world.

Text entity relationship classification method based on small sample learning

A technology of entity relationship and classification method, which is applied in the field of text data recognition, can solve the problems of classification result deviation, relationship classification effect influence, prototype deviation and other problems, and achieve the effect of eliminating error, improving operation speed and solving the problem of feature sparsity

Pending Publication Date: 2022-07-22
HOHAI UNIV
View PDF0 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

Due to the small amount of data in the few-shot learning scenario, when an instance is far away from other instances in the mapping space, it will lead to a huge bias in the average computed prototype.
Once such noise data exists in large quantities, it will have a great impact on the final relationship classification effect; at the same time, for a relationship feature vector, only a part of the dimension has a clear distinction on the final classification result, once extracted from the support set The instance vector has the problem of sparse features, which will cause a large deviation to the final classification result

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
  • Text entity relationship classification method based on small sample learning
  • Text entity relationship classification method based on small sample learning
  • Text entity relationship classification method based on small sample learning

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0043] Below in conjunction with specific embodiments, the present invention will be further illustrated, and it should be understood that these embodiments are only used to illustrate the present invention and not to limit the scope of the present invention. The modifications all fall within the scope defined by the appended claims of this application.

[0044] like figure 1 As shown, the text entity relationship classification method based on few-shot learning includes the following steps:

[0045] Step 1 Given a data set, including support set sentences and query set sentences, use CNN network as an instance encoder to encode the support set sentences and query set sentences, and convert them into low-dimensional instance vectors, so as to obtain the extracted corpus. Entity pair feature. The specific process is:

[0046] 1-1 Select the FewRel dataset that is used more in the field of small sample relation classification;

[0047] 1-2 Predefine a set of relation types f...

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 text entity relationship classification method based on small sample learning. The text entity relationship classification method comprises the following steps: 1) extracting semantic features of instance vectors in a data set by adopting a convolutional neural network as an instance encoder; 2) in a small sample learning scene, endowing each instance with a weight by designing a prototype-level attention mechanism module, and representing a prototype of each relationship in a weighted summation manner; and 3) in a small sample learning scene, replacing a new metric function. Extracting a feature coefficient in a support set vector by using convolution operation through a distance level attention mechanism module, and calculating a distance between each relation prototype and a query instance in a support set by using a product of a Manhattan distance formula and the feature coefficient as a new metric function; and 4) realizing small sample relation classification by utilizing a softmax function.

Description

technical field [0001] The invention relates to a text entity relationship classification method based on small sample learning, and belongs to the technical field of text data recognition. Background technique [0002] As one of the important subtasks of knowledge extraction, relation classification is receiving more and more attention. For unstructured text data, the task of relation classification is to extract the semantic relationship between two or more entities from the text. At present, in relation classification problems, most of the mature technologies achieve excellent experimental results by improving traditional neural network models (such as recurrent neural networks, convolutional neural networks, etc.). However, the datasets selected in the experiment are simple short sentences with predefined categories, and the sample distribution of each relationship is relatively uniform. However, in practical applications, there are often challenges such as small data ...

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): G06F16/35G06F16/33G06F40/205G06K9/62G06N3/04G06N3/08
CPCG06F16/355G06F16/3331G06F40/205G06N3/08G06N3/045G06F18/2415
Inventor 戚荣志高逸飞李水艳赵小涵陈子琦黄倩
Owner HOHAI 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
Eureka Blog
Learn More
PatSnap group products