Document-level remote supervision relationship extraction method and system

A technology of remote supervision and relation extraction, applied in the field of machine learning, can solve the problem of not directly adapting to document-level relation extraction, etc., and achieve the effect of improving the effect.

Active Publication Date: 2021-02-02
TSINGHUA UNIV +1
View PDF4 Cites 2 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

Although early in the sentence-level relation extraction, there have been some works dedicated to denoising distantly supervised corpora by jointly considering multiple sentences, however, these denoising methods cannot be directly adapted to document-level relation extraction.

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
  • Document-level remote supervision relationship extraction method and system
  • Document-level remote supervision relationship extraction method and system
  • Document-level remote supervision relationship extraction method and system

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0043] In order to make the purpose, 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 in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments It is a part of embodiments of the present invention, but not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by persons of ordinary skill in the art without creative efforts fall within the protection scope of the present invention.

[0044] figure 1 A schematic flow chart of the document-level remote supervision relationship extraction method provided by the embodiment of the present invention, as shown in figure 1 As shown, the embodiment of the present invention provides a document-level remote supervision relationship extraction method, including:

[0045] Step 101, acqui...

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 embodiment of the invention provides a document-level remote supervision relationship extraction method and system. The method comprises the following steps: acquiring remote supervision data, based on a trained pre-noise-reduction model, carrying out noise reduction processing on the remote supervision data to obtain target remote supervision data, acquiring the trained pre-noise-reduction model by training sample remote supervision data marked as a positive sample and sample remote supervision data marked as a negative sample, and inputting the target remote supervision data into a trained text encoder model to obtain a document level relationship extraction result, wherein the trained text encoder model is obtained by training noise-reduced sample document level remote supervision data. According to the embodiment of the invention, noise reduction is carried out on the remote supervision data in a pre-training mode, noise in the remote supervision data can be effectively filtered out, and the model is pre-trained by utilizing large-scale noise-reduced data, so that document-level remote supervision relationship extraction is realized, and the document-level relationship extraction effect is improved.

Description

technical field [0001] The invention relates to the technical field of machine learning, in particular to a document-level remote supervision relationship extraction method and system. Background technique [0002] The task of relation extraction aims to identify the relational facts between entities from text, which is the key to realize the automatic construction of knowledge graph. With the development of deep learning technology, the neural relationship extraction model has been verified in the sentence-level relationship extraction task. However, training a high-quality relationship extraction model requires a large number of manually labeled data sets, and the construction of the data set is also difficult. It takes a lot of time and effort. In order to solve this problem, a remote supervision mechanism is proposed, which realizes automatic labeling of data by aligning knowledge graphs and entities in text, thus providing very large-scale data for relation extraction ...

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): G06F16/28G06F16/215G06F40/284G06N3/08
CPCG06F16/288G06F16/215G06F40/284G06N3/08
Inventor 刘知远孙茂松肖朝军姚远谢若冰韩旭林芬林乐宇
Owner TSINGHUA 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