A Distant Supervised Relation Extraction Method Combined with Background Knowledge

A technology of remote supervision and relationship extraction, applied in the field of remote supervision relationship extraction combined with background knowledge, can solve the problem of ignoring the background knowledge of the knowledge base

Active Publication Date: 2021-04-23
PEKING UNIV
View PDF3 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0004] However, the distance-supervised relationship extraction method only uses the knowledge base to label data, and ignores the background knowledge contained in the knowledge base when using the labeled data set to train the classification model and predict the relationship.

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 Distant Supervised Relation Extraction Method Combined with Background Knowledge
  • A Distant Supervised Relation Extraction Method Combined with Background Knowledge
  • A Distant Supervised Relation Extraction Method Combined with Background Knowledge

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0060] In order to make the technical solutions and advantages of the present invention clearer, the present invention will be further described in detail below in conjunction with the accompanying drawings and specific embodiments.

[0061] The importance of background knowledge in natural language understanding has long been recognized. Early natural language processing systems mainly exploited limited linguistic knowledge as background knowledge, for example, human-encoded morphological and syntactic patterns. With the construction of large-scale knowledge bases, knowledge bases such as Freebase, DBpedia, and YAGO contain a large amount of structured semantic knowledge.

[0062] Therefore, in the technical solution of the present invention, a remote supervision relation extraction method combined with background knowledge is proposed.

[0063] figure 1 It is a flow chart of the remote supervision relationship extraction method combined with background knowledge in the embod...

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 provides a remote supervision relation extraction method combined with background knowledge. The method includes: for each bag in the training data set, obtain the vector representation of each sentence in the bag through the sentence encoder; use the entity representation in the knowledge base to construct a sentence-level attention mechanism, and assign attention to each sentence Weight, and based on the attention weight of each sentence to obtain the unique semantic vector of each package; use the relationship vector in the knowledge base to perform relation retrieval on the semantic vector of the package; train the entire relation extractor according to the unified objective function. The application of the invention can alleviate the problem of mislabeling in remote supervision and improve the accuracy of relationship prediction.

Description

technical field [0001] The present application relates to the technical field of natural language processing, in particular to a remote supervision relation extraction method combined with background knowledge. Background technique [0002] Information extraction is an important research field in natural language processing. Its task is to extract structured information from large-scale unstructured or semi-structured natural language texts, and relation extraction is one of the important subtasks. The purpose of relation extraction is to extract the semantic relationship between entities from the text, for example, the sentence "Bill Gates is the founder of Microsoft Inc." contains an entity pair (Bill Gates, Mircrosoft), the task of relation extraction is to identify this Entity pairs have a relationship of "Founder". [0003] Supervised learning methods treat relation extraction as a classification problem and require a large amount of manually labeled training corpus, w...

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): G06F16/36
Inventor 邓可君章学妙范红杰柳军飞
Owner PEKING 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
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