Unlock instant, AI-driven research and patent intelligence for your innovation.

Method and device for generating problem based on sequence generation model of template

A technology of sequence generation and model generation, applied in semantic analysis, instrumentation, electronic digital data processing, etc., can solve problems such as single types, lack of language diversity, and single problem types, and achieve the effect of flexible types and rich language types

Pending Publication Date: 2021-05-25
ZHEJIANG GONGSHANG UNIVERSITY
View PDF9 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0002] At present, a large part of the research on Chinese question generation in the field of natural language processing is based on knowledge graphs constructed by templates or rule-based models. Due to the limitations of templates and rules, the types of questions generated are single and the language is inflexible.
[0003] Rule-based methods usually require a lot of manpower and time, and the generated questions usually have problems with sentences that are not smooth and do not match the content of the article
The questions generated by the template-based method are relatively rigid, single-type, and lack of language diversity, and the quality of the template directly determines the quality of the generated questions.
The question generation method based solely on the sequence model has problems such as unclear subject entity recognition, which also affects the quality of generated questions

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
  • Method and device for generating problem based on sequence generation model of template
  • Method and device for generating problem based on sequence generation model of template
  • Method and device for generating problem based on sequence generation model of template

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0046] In order to make the purpose, technical solutions and advantages of the embodiments of the present disclosure clearer, the technical solutions of the embodiments of the present disclosure will be clearly and completely described below in conjunction with the drawings of the embodiments of the present disclosure. Apparently, the described embodiments are some of the embodiments of the present disclosure, not all of them. Based on the described embodiments of the present disclosure, all other embodiments obtained by persons of ordinary skill in the art without creative effort fall within the protection scope of the present disclosure.

[0047] Unless otherwise defined, the technical terms or scientific terms used in the embodiments of the present disclosure shall have ordinary meanings understood by those skilled in the art to which the present disclosure belongs. The words "comprising" or "comprising" and other similar words used in the embodiments of the present disclos...

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 method and a system for generating a problem based on a sequence generation model of a template, and the method comprises the steps of constructing a text extraction model, classifying texts for generating the problem, and obtaining a prediction text; constructing a text recognition model, converting a text into vector representation by the text recognition model, obtaining input sequences corresponding to word vectors and word vectors based on the vector representation and word level and statement level attention mechanisms set in the model, and performing classification based on the input sequences to obtain prediction relation labels of a predicted text; and constructing a sequence generation model, receiving the problem by a coding unit, mapping the problem into a multivariate vector, inputting the multivariate vector into a template decoding unit, and replacing a problem template output by the decoding unit at the moment according to the prediction and the prediction relation label.

Description

technical field [0001] The invention relates to the technical field of artificial intelligence natural language processing, in particular to a method and device for generating a sequence generation model based on a template. Background technique [0002] At present, a large part of the research on Chinese question generation in the field of natural language processing is based on knowledge graphs constructed by templates or rule-based models. Due to the limitations of templates and rules, the types of questions generated are single and the language is inflexible. . [0003] The rule-based method usually consumes a lot of manpower and time, and the generated questions usually have the problem that the sentence is not smooth and does not match the content of the article. The questions generated by the template-based method are relatively rigid, with a single type and lack of language diversity, and the quality of the template directly determines the quality of the generated q...

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): G06F40/186G06F40/30G06F16/36G06F16/35
CPCG06F40/186G06F40/30G06F16/35G06F16/367Y02D10/00
Inventor 李玉娥董黎刚蒋献吴梦莹诸葛斌
Owner ZHEJIANG GONGSHANG UNIVERSITY
Features
  • R&D
  • Intellectual Property
  • Life Sciences
  • Materials
  • Tech Scout
Why Patsnap Eureka
  • Unparalleled Data Quality
  • Higher Quality Content
  • 60% Fewer Hallucinations
Social media
Patsnap Eureka Blog
Learn More

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

© 2025 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap|About US| Contact US: help@patsnap.com