Semantic role labeling method based on synergetic neural network

A collaborative neural network and semantic role labeling technology, applied in the field of semantic role labeling based on collaborative neural network, can solve problems affecting performance, labeling bias, etc., to achieve improved separability, high labeling performance, good application prospects and applications value effect

Active Publication Date: 2012-09-12
深圳云译科技有限公司
View PDF2 Cites 33 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

But there will be a label bias problem that will affect the final performance

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
  • Semantic role labeling method based on synergetic neural network
  • Semantic role labeling method based on synergetic neural network
  • Semantic role labeling method based on synergetic neural network

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0043] The present invention will be further described below in conjunction with accompanying drawing and embodiment:

[0044] The order parameter construction is ultimately determined by the prototype mode, so the choice of the prototype mode has a decisive impact on the recognition of the collaborative neural network, and is also the basis for the excellent performance of its collaborative algorithm. The traditional Haken collaborative neural network requires that the patterns remain uncorrelated, but it is not easy to achieve in actual processing, especially for semantic annotations with rich features and complex patterns. With more and more With the addition of features, the interaction between features is becoming more and more serious, so we consider changing the feature space of the mode to reduce the correlation between the modes, and combine or decompose the features through the kernel-based method, and the low-dimensional space Mapped to a high-dimensional feature sp...

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 semantic role labeling method based on a synergetic neural network, and relates to the fields of semantic role labeling, mode identification and synergetic neural networks, in particular to a method for introducing the principle of the synergetic neural network into shallow semantic analysis. The semantic role labeling method comprises the following steps: extracting characteristics from training language material and testing language material and constructing corresponding semantic characteristic vectors; performing kernel transformation on the semantic characteristic vectors and constructing a prototype pattern and a mode to be tested on the basis; constructing an order parameter and calculating a plurality of candidate roles for each dependent component; constructing a predicate base and combining the candidate roles of all the dependent components corresponding each predicate to get role chains of all the predicates; and optimizing a network parameter, performing dynamic evolution on the synergetic neural network to get an optimal role chain, and outputting the labeling mode. The principle of the synergetic neural network is firstly introduced into the semantic role labeling, and the method can be widely applicable to various natural language processing tasks. The semantic role labeling method has better application prospects and application value.

Description

technical field [0001] The invention relates to the fields of semantic role labeling, pattern recognition and collaborative neural network, relates to a method for introducing the principle of collaborative neural network into shallow semantic analysis, and in particular to a semantic role labeling method based on the collaborative neural network. Background technique [0002] As a main research direction of natural language processing, semantic analysis can transform natural language into a formal language that computers can understand, so as to achieve mutual understanding between humans and computers. Correct semantic analysis of sentences has always been the main goal pursued by scholars engaged in natural language understanding research. However, limited by the complexity of semantics, current semantic analysis mainly focuses on role labeling and other aspects. Semantic role labeling does not carry out detailed semantic analysis on the entire sentence, it only labels t...

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): G06F17/27G06F17/30
Inventor 陈毅东黄哲煌史晓东周昌乐
Owner 深圳云译科技有限公司
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