Unlock instant, AI-driven research and patent intelligence for your innovation.

Multi-feature Chinese entity relation extraction method based on deep learning

A technology of entity relationship and deep learning, applied in the direction of neural learning methods, database models, instruments, etc., can solve the problem that the performance of neural network models is not as good as that of English corpus, and achieve the effect of solving the unsatisfactory effect of relationship extraction

Pending Publication Date: 2022-07-15
ZHEJIANG UNIV OF TECH
View PDF0 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

Finally, the performance of the existing neural network model on the Chinese corpus is not as good as that of the English corpus. This is the difficulty brought about by the difference between Chinese grammar and English.

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
  • Multi-feature Chinese entity relation extraction method based on deep learning
  • Multi-feature Chinese entity relation extraction method based on deep learning
  • Multi-feature Chinese entity relation extraction method based on deep learning

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0044] In order to make the purposes, technical solutions and advantages of the embodiments of the present invention clearer, the technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings and specific embodiments. Obviously, the described embodiments are of the present invention. Some examples, but not all examples. Based on the embodiments of the present invention, all other embodiments obtained by those of ordinary skill in the art without creative efforts shall fall within the protection scope of the present invention.

[0045] A method based on deep learning multi-feature Chinese relation extraction, such as figure 1 shown, including multi-feature Chinese embedding, recurrent convolutional network, max pooling layer, softmax classifier.

[0046] Specific steps are as follows:

[0047] Step 1: Multi-feature Chinese word embedding: Use the BERT model to learn character vectors, c...

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 multi-feature Chinese entity relation extraction method based on deep learning, and particularly relates to the technical field of natural language processing. BERT learning character vectors are used for splicing part-of-speech tags and character information position information to serve as word embedding vector input to be sent to a multi-feature cyclic convolutional network, the neural network comprises Chinese sentence-level features and character-level features, and the Chinese sentence-level features and the character-level features are sent to a softmax classifier as final classification vectors through a maximum pooling layer. For each sentence, the category corresponding to the value with the maximum probability is a classification result. The method is suitable for relation extraction of Chinese texts, and can effectively aim at complex relations of Chinese corpora.

Description

technical field [0001] The invention relates to the technical field of natural language processing, in particular to a deep learning-based multi-feature Chinese entity relationship extraction method. Background technique [0002] Relation extraction is to extract the relationship between entities in the text on the basis of named entity recognition, and form a triple form of <entity 1, relationship, entity 2>. [0003] Early relationship extraction was based on rule patterns and later based on machine learning. Machine learning-based relationship extraction can be divided into supervised, semi-supervised, unsupervised, open domain-oriented, and remotely supervised entity relationship extraction. At present, the rise of deep learning and the development of natural language processing technology and big data technology have ushered in a significant improvement in relation extraction. At present, relation extraction is mainly used in the construction of knowledge graphs,...

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): G06F40/30G06F40/253G06F40/289G06N3/04G06N3/08G06F16/28
CPCG06F40/30G06F40/253G06F40/289G06N3/08G06F16/288G06N3/047G06N3/045
Inventor 张文安张明德刘强刘涛傅金波金聪朱琦
Owner ZHEJIANG UNIV OF TECH