Vietnamese News Event Detection Method Based on Chinese Information and Vietnamese Syntax Guidance

A kind of event detection, Chinese technology, applied in neural learning methods, network data retrieval, other database retrieval, etc., can solve the problem of scarcity of labeled data, and achieve the effect of eliminating event ambiguity and event type ambiguity

Active Publication Date: 2022-03-25
KUNMING UNIV OF SCI & TECH
View PDF6 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

The current event detection models based on deep learning rely on a sufficient amount of labeled data and only focus on specific information such as trigger words. However, the scarcity of Vietnamese news event annotation data and the event ambiguity caused by trigger words have brought great challenges to Vietnamese event detection. big challenge

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
  • Vietnamese News Event Detection Method Based on Chinese Information and Vietnamese Syntax Guidance
  • Vietnamese News Event Detection Method Based on Chinese Information and Vietnamese Syntax Guidance
  • Vietnamese News Event Detection Method Based on Chinese Information and Vietnamese Syntax Guidance

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0069] Embodiment 1: as Figure 1-6 As shown, the Vietnamese news event detection method based on Chinese information and Vietnamese syntax guidance, the specific steps are as follows:

[0070] Step1. Collect news texts for the detection of Chinese-Vietnamese bilingual related news events, and deduplicate and screen the news texts;

[0071] Step2. Formulate the labeling system of Chinese-Vietnamese bilingual news event types and Chinese trigger words, and divide the marked Vietnamese news corpus into training corpus, test corpus and verification corpus;

[0072] Step3. Use two network modules, the shared encoder network and the cross-attention network, to fuse bilingual information.

[0073] Step4. Use syntactic graph convolution to jointly learn Vietnamese vector representation and Vietnamese dependent syntactic information, and obtain a vector representation that fuses dependent syntactic information.

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 relates to a Vietnamese news event detection method based on Chinese information and Vietnamese syntax guidance, and belongs to the technical field of natural language processing. The present invention first enables Vietnamese sentences to obtain Chinese semantic information in the bilingual information fusion module. Then, according to the Vietnamese syntactic dependencies, syntactic graph convolution is used to enhance the association between information to resolve the multi-event ambiguity problem. Finally, the event type perception network is used to extract the Vietnamese sentence representation based on the Chinese event type to complete the event detection of Vietnamese. The event detection of the present invention needs to identify and classify the event information in the news. At present, in view of the scarcity of Vietnamese news event labeling data and the ambiguity of event types, according to the characteristics of multilingual consistency, the use of rich Chinese labeling data can solve the problem of Vietnamese language. Data scarcity and event type ambiguity.

Description

technical field [0001] The invention relates to a Vietnamese news event detection method based on Chinese information and Vietnamese syntax guidance, and belongs to the technical field of natural language processing. Background technique [0002] Event detection is to identify event information from unstructured text and classify it. The issues of common concern between China and Vietnam are increasing day by day, and the related news reports are also increasing. Detecting the events in the news related to China and Vietnam reported in the Vietnam news will help the relevant departments to grasp the dynamics and orientation of the situation in Vietnam and make correct decisions. Responses. The current event detection models based on deep learning rely on a sufficient amount of labeled data and only focus on specific information such as trigger words. However, the scarcity of Vietnamese news event annotation data and the event ambiguity caused by trigger words have brought g...

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): G06F40/284G06F40/295G06F16/951G06F40/126G06F40/211G06N3/04G06N3/08
Inventor 张亚飞陈龙郭军军余正涛
Owner KUNMING UNIV OF SCI & 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