Entity relation joint extraction method and device based on neural network

An entity relationship, neural network technology, applied in neural learning methods, biological neural network models, neural architectures, etc., can solve problems such as weakening task interaction, accumulating errors, and difficulty in extracting news texts quickly and efficiently, achieving nested The effect of overlapping entities and relationships, avoiding exposure bias

Pending Publication Date: 2021-10-01
浙江华巽科技有限公司
View PDF0 Cites 17 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

The separate "pipeline" approach to named entity recognition and relationship extraction has the following problems: the error generated by the named entity recognition task will be propagated to the relationship extraction task to form a cumulative error, and the named entity recognition may ge...

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 relation joint extraction method and device based on neural network
  • Entity relation joint extraction method and device based on neural network
  • Entity relation joint extraction method and device based on neural network

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0018] The technical solutions provided by the present invention will be described in detail below in conjunction with specific examples. It should be understood that the following specific embodiments are only used to illustrate the present invention and are not intended to limit the scope of the present invention.

[0019] A neural network-based entity-relationship joint extraction method disclosed in the embodiment of the present invention, its model framework is as follows figure 1 As shown, the process is as follows figure 2 As shown, the specific implementation steps are as follows:

[0020] Step 1, word information fusion. Pre-trained language models can effectively improve the performance of natural language processing tasks. When the model learns more prior knowledge, more reliable language representation can be obtained. Among them, the pre-trained language model BERT has reached the highest level in many natural language processing tasks, but the training of BERT...

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 an entity relation joint extraction method and device based on a neural network. The method comprises the following steps: firstly, fusing a pre-trained ERNIE word vector, a pre-trained CWV word vector and relative position information of words by utilizing a single-layer Transform network; secondly, improving a handshake labeling strategy, and introducing a vectorized entity type label to make full use of entity type information; then, obtaining candidate entity relationship triples in the sentences through an annotation decoding method; and finally, indexing articles, sentences, entities and relationships by using UCL according to the characteristics that the UCL national standard can efficiently organize contents and effectively associate information. The entity relationship triple can be directly extracted from the sentence, the problems of redundant entities, nested entities, overlapping relationships and the like are avoided, a small amount of annotation data can be used for quickly checking the entity relationship, and the data can be objectively and normatively indexed.

Description

technical field [0001] The invention relates to a neural network-based entity relationship joint extraction method and device, and belongs to the technical field of the Internet and artificial intelligence. Background technique [0002] With the continuous development of the Internet industry, the data in the Internet is growing at an exponential rate, which contains a wealth of knowledge and information. Only by extracting structured entity and relationship information from unstructured text data through entity-relationship joint extraction method, and organizing structured information reasonably and efficiently, can we fully mine and utilize the interrelated information in the text, and then realize the content governance. In traditional relation extraction, named entity recognition is always used as the predecessor task of relation extraction task, that is, relation extraction is performed on the basis of named entity recognition task. Separating the two tasks makes the...

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): G06F40/295G06F40/30G06F40/117G06F40/126G06N3/04G06N3/08
CPCG06F40/295G06F40/30G06F40/117G06F40/126G06N3/04G06N3/084
Inventor 杨鹏程昌虎谢亮亮方海生
Owner 浙江华巽科技有限公司
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