Semi-automatic demand extraction method based on pre-training language fine tuning and dependency features

A pre-training and semi-automatic technology, applied in the field of information extraction of natural language processing, can solve problems such as opaque capture rules of BERT, poor interpretability of deep learning, time-consuming BERT model training, etc., to improve interpretability and reliability Effect

Pending Publication Date: 2022-03-22
BEIJING UNIV OF TECH
View PDF0 Cites 2 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

However, the shortcomings of the BERT model in engineering research are also very prominent. The training of the BERT model is time-consuming and requires a large amount of hardware computing power support; the interpretability of deep learning is not good, which makes the rules captured by BERT relatively opaque; in order to improve training performance , need to pre-label a large amount of corpus data for fine-tuning training
Therefore, for domain-specific tasks with fewer data sets, fully using the pre-trained language model has cost and performance concerns.

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
  • Semi-automatic demand extraction method based on pre-training language fine tuning and dependency features
  • Semi-automatic demand extraction method based on pre-training language fine tuning and dependency features
  • Semi-automatic demand extraction method based on pre-training language fine tuning and dependency features

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0027] A brief overview of the invention is given below in order to provide a basic understanding of some aspects of the invention. It should be understood that this summary is not an exhaustive overview of the invention. It is not intended to identify key or critical parts of the invention nor to delineate the scope of the invention. Its purpose is merely to present some concepts in a simplified form as a prelude to the more detailed description that is discussed later.

[0028] Such as figure 1 As shown, the semi-automatic requirement extraction method includes the following steps: preprocessing step, entity extraction step, entity fusion confirmation step, intent extraction step, intent fusion confirmation step, subject relationship post-processing step and output modeling. For the components required by the iStar target model, the subject (Actor) and resource (Resource) are processed in the entity extraction, the dependency between the intent elements such as the task (Tas...

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 semi-automatic demand extraction method based on pre-training language fine tuning and dependency features. The semi-automatic demand extraction method comprises the following steps of preprocessing, entity extraction, entity fusion confirmation, intention extraction, intention fusion confirmation, subject relation post-processing and output modeling. According to the semi-automatic demand extraction method provided by the invention, the advantages of a pre-training language fine tuning model and dependency analysis characteristics are fused: on one hand, rules are designed for the field problem of software demand modeling, and the interpretability and reliability of the system are improved through field knowledge; and on the other hand, proper fine adjustment is performed by utilizing the generalization convenience of the pre-training language model, and additional large-scale data set labeling training cannot be paid for the accuracy premium.

Description

technical field [0001] The present invention relates to the technical field of information extraction of natural language processing, especially a semi-automatic requirement extraction method based on pre-trained language fine-tuning model and dependent syntactic feature analysis, which is suitable for iStar target model modeling of English software requirement documents described in natural language Analysis process. Background technique [0002] In the current field of software engineering, software requirements are the focus of stakeholders of software projects. With the continuous development of the information technology industry, the volume of software projects is increasing day by day, and complex and huge requirements are systematically collected, analyzed and managed, and software requirements engineering emerges as the times require. As one of the most important and complex links in software requirements engineering, requirements modeling should be able to clearly...

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): G06F8/10G06F16/25G06F40/295G06N3/04
CPCG06F8/10G06F16/258G06F40/295G06N3/045
Inventor 李童周祺翔王云铎党鸿博
Owner BEIJING UNIV OF 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