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

Two-stage problem generation system oriented to problems

A question and stage technology, applied in the field of two-stage question generation system, can solve problems such as insufficient use of questions and insufficient attention to answers

Pending Publication Date: 2020-10-23
SHANGHAI JIAO TONG UNIV
View PDF0 Cites 10 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0005] Aiming at the problems of insufficient use of questions and insufficient attention to answers in the prior art, the present invention proposes a question-oriented two-stage question generation system,

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
  • Two-stage problem generation system oriented to problems
  • Two-stage problem generation system oriented to problems
  • Two-stage problem generation system oriented to problems

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0017] Such as figure 1 As shown, this embodiment relates to a two-stage question generation system based on an end-to-end network, including: a question-and-answer data preprocessing module, a context sequence labeling module, and a question generation module, wherein: the question-and-answer data preprocessing module performs data set The re-division, feature extraction and dictionary construction are carried out and the features and words are vectorized to obtain the labeled training set and real labels; the context sequence labeling module uses the labeled data set for network model training and obtains the context prediction label; the question generation module uses the real label and the prediction label as input to generate a sequence of prediction questions, and the final maximum probability prediction problem is obtained through backpropagation training with the error of the real problem.

[0018] The experimental data in this embodiment comes from Stanford’s open so...

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

A question-oriented two-stage question generation system comprises a question and answer data preprocessing module, a context sequence labeling module and a question generation module, the question and answer data preprocessing module performs re-division, feature extraction and dictionary construction on a data set and vectorizes features and words to obtain a labeling training set and real labels; the context sequence marking module performs network model training by adopting the marking data set and obtains a prediction label of the context; and the problem generation module generates a prediction problem sequence by taking the real label and the prediction label as inputs, and performs back propagation training with an error of the real problem to obtain a final maximum probability prediction problem. According to the invention, the indexes of the BLEU, the MENTOR and the ROUGE-L are obviously improved.

Description

[0001] This application is a divisional application with application number [201911179784.8] application date [2019 / 11 / 27] title [problem-oriented two-stage question generation system]. technical field [0002] The invention relates to a technology in the field of natural language processing, in particular to a problem-oriented two-stage problem generation system. Background technique [0003] Question generation (QG), which aims to generate questions from various natural language texts, plays a crucial role in natural language generation. In recent years, question generation has attracted increasing attention due to its wide range of applications. The most intuitive application is to expand the dataset of the question answering task, thereby improving the performance of the task. Questions can help readers assess their grasp of the context and remind them of possible omissions in the reading process, which is of great significance in the education industry to reduce the bu...

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): G06F16/332G06F40/216G06F40/30G06F40/253G06N3/04G06N3/08G06Q50/20
CPCG06F40/216G06F40/30G06F40/253G06F16/3329G06N3/049G06N3/084G06Q50/20G06N3/045
Inventor 沈耀倪茂森过敏意姚斌陈全
Owner SHANGHAI JIAO TONG 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