Supercharge Your Innovation With Domain-Expert AI Agents!

Event extraction method fusing pre-training language model and anti-noise interference remote supervision information

A remote supervision and event extraction technology, applied in neural learning methods, biological neural network models, digital data information retrieval, etc., can solve problems affecting model accuracy, wrong guidance information, affecting event prediction and extraction

Pending Publication Date: 2021-08-31
NANJING UNIV +1
View PDF13 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

However, in addition to bringing external knowledge information, remote supervision will also bring wrong guidance information, and the introduction of noise interference will affect the accuracy of the judgment of the model.
The insufficiency of RNN and CNN in text representation ability also affects the prediction and extraction of events

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
  • Event extraction method fusing pre-training language model and anti-noise interference remote supervision information
  • Event extraction method fusing pre-training language model and anti-noise interference remote supervision information
  • Event extraction method fusing pre-training language model and anti-noise interference remote supervision information

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0030] In order to make the purpose, technical solution and advantages of the present application clearer, the present application will be further described in detail below in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described here are only used to explain the present application, and are not intended to limit the present application.

[0031] In one embodiment, the present invention proposes an event extraction method that fuses pre-trained language models and anti-noise interference remote supervision information, the method includes the following steps:

[0032] Step 1, training data corpus collection, Internet text data obtained through the crawler, and the data in the form of text is stored in the form of a .txt file through the crawler.

[0033] Step 2. Perform preprocessing operations on the labeled data, including removing html tags and special symbols, and dividing the text into short texts in 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 provides an event extraction method fusing a pre-training language model and anti-noise interference remote supervision information, and belongs to the technical field of computers. According to the method, a comprehensive knowledge auxiliary model is used for judgment, a pre-training language model which is formed by introducing mass text pre-training and comprises a large amount of semantic grammar knowledge information is used as a network structure unit of an event extraction model; and a model algorithm mixed with anti-noise interference remote supervision features is used, and a gradient direction under a circular constraint condition is added to carry out anti-interference training. According to the method, richer text information can be represented, and meanwhile, the resistance of the model to noise errors can be improved through anti-interference training when remote supervision features are introduced.

Description

technical field [0001] The invention relates to an event extraction method for integrating pre-trained language models and anti-noise interference remote supervision information, in particular to the technical field of computer data processing. Background technique [0002] With the continuous deepening of informatization construction in the Internet era, massive Internet information has shown explosive growth. How to use Internet information to assist industry decision-making has become the focus of attention of enterprises and even governments and countries. Information from the Internet often appears in the form of text, usually from channels such as news manuscripts and forum replies, and generally presents the characteristics of no structure and multiple redundancy. It needs to be read and understood to locate the key information in the text and filter irrelevant content. Event extraction is to present the data content of unstructured text in a structured form, extract ...

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): G06F16/35G06F16/383G06K9/62G06N3/04G06N3/08
CPCG06F16/35G06F16/383G06N3/04G06N3/084G06F18/25G06F18/24G06F18/214Y02D10/00
Inventor 李书棋高阳
Owner NANJING UNIV
Features
  • R&D
  • Intellectual Property
  • Life Sciences
  • Materials
  • Tech Scout
Why Patsnap Eureka
  • Unparalleled Data Quality
  • Higher Quality Content
  • 60% Fewer Hallucinations
Social media
Patsnap Eureka Blog
Learn More

Browse by: Latest US Patents, China's latest patents, Technical Efficacy Thesaurus, Application Domain, Technology Topic, Popular Technical Reports.

© 2025 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap|About US| Contact US: help@patsnap.com