A multi-triple extraction method based on an entity-relationship joint extraction model

An entity relationship and triplet technology, applied in the field of text processing, can solve the problems of not learning, unable to correctly detect/select multi-triple target relationships, confusing classifiers, etc., to achieve intensive training, strong multi-triple Effect of group extraction ability

Active Publication Date: 2019-01-08
NAT UNIV OF DEFENSE TECH
View PDF3 Cites 57 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

On the other hand, models (Miwa and Bansal, 2016; Zheng et al., 2017a) assume that each entity pair has some kind of relationship, in which case a large number of pairs need to be thrown into a single entity called "other" class, but the "other" features are not learned during classifier training, so noisy entities (Elysee Palace) and unexpected relations like Donald Trump, Elysee Palace confuse the classifier
Therefore, multi-triple target relations may not be detected / selected correctly

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
  • A multi-triple extraction method based on an entity-relationship joint extraction model
  • A multi-triple extraction method based on an entity-relationship joint extraction model
  • A multi-triple extraction method based on an entity-relationship joint extraction model

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0044] In order to make the object, technical solution and advantages of the present invention clearer, the present invention will be described in further detail below in conjunction with specific embodiments and with reference to the accompanying drawings.

[0045] As an embodiment of the present invention, see figure 1 As shown, it is a schematic flowchart of a method for extracting multiple triples based on an entity-relationship joint extraction model according to an embodiment of the present invention. The described multi-triple extraction method based on the joint entity-relationship extraction model includes:

[0046] Step 101: Acquire text, perform sentence segmentation processing on the target text, and perform three-part tokenization on each word in the sentence.

[0047] The three-part marking of each word in the sentence includes marking the position, type, and relationship of each word in the sentence; the position mark (Position Part, PP) is used to describe th...

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-triple extraction method based on an entity-relationship joint extraction model, which is characterized in that the method comprises the following steps: obtaining text, processing target text in clauses, and carrying out position, type and relation mark on each word in a sentence; establishing an entity-relationship joint extraction model; training the entity-relationship joint extraction model; according to entity-relation joint extraction model, carrying out three-tuple extraction. The three-part marking scheme designed by the invention can exclude entities that are not related to the target relationship in the process of entity relationship joint extraction. In addition, the multi-triple extraction method based on the entity-relationship joint extractionmodel can be used for extracting the multi-triple, and the model based on the triple extraction method of the invention has stronger multi-triple extraction ability compared with other models.

Description

technical field [0001] The invention relates to the technical field of text processing, in particular to a multi-triple extraction method based on an entity-relationship joint extraction model. Background technique [0002] Triple extraction obtains structured information (simultaneously extracting two entities and the relationship between them) from unstructured text, which is an important and key step in the construction of automatic knowledge bases. Traditional models use named entities separately. Recognition (NER) (Shaalan, 2014) and Relation Classification (RC) (Rink and Harabagiu, 2010) extract entities and relations, yielding the final triples. This modular approach cannot fully capture and exploit the correlation between the tasks of NER and RC, and is prone to cascading errors (Li and Ji, 2014). [0003] To overcome these shortcomings, a joint extraction model was proposed. Most of them are feature-structural models (Kate and Mooney, 2010; Yu and Lam, 2010; Chan ...

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): G06F17/27G06F16/36G06N3/04
CPCG06F40/211G06N3/045G06F40/295G06F40/117G06N3/082G06N3/047G06N3/044G06N3/08
Inventor 赵翔谭真郭爱博葛斌郭得科肖卫东唐九阳黄旭倩
Owner NAT UNIV OF DEFENSE TECH
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