Looking for breakthrough ideas for innovation challenges? Try Patsnap Eureka!

Recurrent neural network event sequential relationship recognition method based on semantic attention

A time-series relationship and attention technology, applied in semantic analysis, natural language data processing, special data processing applications, etc., can solve problems such as difficulty in capturing semantic information, lack of effective connection and fusion information for different word segmentations, etc.

Pending Publication Date: 2020-05-15
HANGZHOU DIANZI UNIV
View PDF0 Cites 5 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0008] The present invention provides a recurrent neural network event timing relationship recognition method based on a semantic attention mechanism, aiming to solve the problems existing in the current event timing relationship recognition method that it is difficult to capture the hidden semantic information in event sentences and the lack of effective connections between different word segmentations and the problem of fusing information

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
  • Recurrent neural network event sequential relationship recognition method based on semantic attention
  • Recurrent neural network event sequential relationship recognition method based on semantic attention
  • Recurrent neural network event sequential relationship recognition method based on semantic attention

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0032] In order to make the skilled person better understand the present invention, the present invention will be further explained below in conjunction with the accompanying drawings and specific examples, and the specific details are as follows:

[0033] The present invention comprises the following steps:

[0034] Step1: Build trigger word semantic dependency branch. Trigger words are predicates used to identify events, usually verbs and nouns. First, perform syntactic dependency analysis on the input event sentence, obtain a complete dependency syntax tree, find the position of the trigger word, find its parent node and sibling node, until the end of the root node; if the trigger word is not a leaf node, start from the trigger word The word position recursively looks down its child nodes. After the analysis of the experimental results, the recursive downward search twice has the best effect. This method can effectively capture the implicit semantic information in the eve...

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 recurrent neural network event sequential relationship recognition method based on semantic attention, and the method mainly comprises the following steps: firstly carrying out syntactic dependency analysis on an inputted event sentence, intercepting a related trigger word semantic dependency branch, and then obtaining a corresponding hidden state vector through a recurrent neural network; then, calculating attention weight vectors except the trigger word, fusing different segmented words according to different weights, then splicing the fused segmented words with thetrigger word, and obtaining event sentence state vectors; and finally, putting the event sentence state vector into a softmax function to predict a time sequence relationship. According to the method, semantic information implied in event sentences can be effectively captured, and different segmented words can be effectively associated and fused, so that the event sequential relationship recognition precision is improved.

Description

technical field [0001] The invention relates to the field of natural language processing, in particular to a method for recognizing the time sequence relationship of events in a cyclic neural network based on semantic attention. Background technique [0002] As an important form of knowledge representation, events have received extensive attention in the field of natural language processing. An event is a set of related descriptions about a topic. As an important means of conveying information, it objectively depicts the occurrence of a specific subject (some or some people and objects) in a specific time and place environment. one thing. The event sequence relationship refers to the time sequence relationship between events when they occur. It is a semantic relationship between events, which connects the evolution process of a subject event from the beginning to the end and the interrelationship of events. Examples of event timing relationship recognition (taken from the ...

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): G06F40/289G06F40/30G06F16/35
CPCG06F16/355
Inventor 徐小良高通王宇翔
Owner HANGZHOU DIANZI UNIV
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Patsnap Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Patsnap Eureka Blog
Learn More
PatSnap group products

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

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap|About US| Contact US: help@patsnap.com