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

Deep dialogue semantic role labeling method and system based on knowledge enhancement

A semantic role labeling and in-depth technology, applied in semantic analysis, natural language data processing, instruments, etc., can solve problems such as poor results, and achieve the effect of solving poor results and improving accuracy

Pending Publication Date: 2021-05-07
SUN YAT SEN UNIV
View PDF5 Cites 4 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Benefits of technology

The technical effect of this patented technology is how it proposes an approach for annotating deep concepts like personality or location into models called fuzzy logic networks (FLNs). These maps help us better interpret complex conversational situations by showing them more clearly than previous methods such as time stamp analysis.

Problems solved by technology

In this patented problem addressed in the technical solution described in the patents, there was no existing way for sematic roles labels to be applied across different types of documents accurately without sacrificing their effectiveness over other forms such as narrative domains due to human factors involved in conversation-based interactions.

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
  • Deep dialogue semantic role labeling method and system based on knowledge enhancement
  • Deep dialogue semantic role labeling method and system based on knowledge enhancement
  • Deep dialogue semantic role labeling method and system based on knowledge enhancement

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0039] The present invention will be further described in detail below in conjunction with the accompanying drawings and specific embodiments. For the step numbers in the following embodiments, it is only set for the convenience of illustration and description, and the order between the steps is not limited in any way. The execution order of each step in the embodiments can be adapted according to the understanding of those skilled in the art sexual adjustment.

[0040] refer to figure 1 with image 3 , the present invention provides a knowledge-enhanced deep dialog semantic role labeling method, the method comprising the following steps:

[0041] Obtain the data set and preprocess the data set to obtain the preprocessed text;

[0042] Specifically, in each Batch (Batch is a collection of multi-section text data. In actual training, the data is based on Batch as a unit, and the text inside is trained in parallel), and each section is obtained through data preprocessing (mai...

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 deep dialogue semantic role labeling method and system based on knowledge enhancement, and the method comprises the steps: obtaining a data set, preprocessing the data set, and obtaining a preprocessed text; obtaining a triple, and screening the triple to obtain a filtered triple; combining the filtered triple with the preprocessed text to obtain a sentence tree structure; converting the sentence tree structure into a sequence, inputting the sequence into a BERT encoder, and outputting a word vector; processing the preprocessed text to obtain an index vector; and inputting the word vector and the index vector into a pre-constructed semantic role labeling model, and outputting a prediction labeling result. The system comprises a preprocessing module, a triple module, a tree structure module, a word vector module, an index vector module and a result module. Marking accuracy is improved. The deep dialogue semantic role labeling method and system based on knowledge enhancement can be widely applied to the technical field of natural language processing.

Description

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

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
Owner SUN YAT SEN 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