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

A Conversational Question Generation Method Based on Reinforced Dynamic Reasoning

A conversational, question-based technology, applied in the field of conversational question generation based on enhanced dynamic reasoning, to achieve the effect of improving quality

Active Publication Date: 2021-03-30
ZHEJIANG UNIV
View PDF24 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0004] Previous work is based on a dialogue history or an article to generate text, but combining the two as input is a more challenging and practical work

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
  • A Conversational Question Generation Method Based on Reinforced Dynamic Reasoning
  • A Conversational Question Generation Method Based on Reinforced Dynamic Reasoning
  • A Conversational Question Generation Method Based on Reinforced Dynamic Reasoning

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0039] The present invention will be further described in detail below with reference to the accompanying drawings and embodiments. It should be noted that the following embodiments are intended to facilitate the understanding of the present invention, but do not limit it in any way.

[0040] Such as figure 1 As shown, a conversational question generation method based on enhanced dynamic reasoning, the structure of the whole method is as follows figure 2 As shown, it specifically includes the following steps:

[0041] S01. Find a reference text in a given article by using a rule method. Use CoQA, a large-scale comprehensive corpus, as the training set, and use the reference text given in the dataset as the input for training. For datasets without a given reference text, each article is divided into sections, and each sentence becomes the reference text of each round of dialogue in sequence. Finally, the reference text is fed into the subsequent question generation model as...

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 dialogue type question generation method based on enhanced dynamic reasoning. The dialogue type question generation method comprises the following steps: (1) finding out a section of reference text in a given article by utilizing a rule method; (2) constructing a problem generation model comprising an encoder and a decoder, inputting a dialogue history and a reference text, and encoding the dialogue history and the reference text by using the encoder to obtain an expression matrix; (3) performing dynamic reasoning on the obtained expression matrix to obtain a reasoning matrix; (4) taking the reasoning matrix obtained in the step (3) as an initial parameter of a long and short term memory network hiding unit in a decoder, and outputting words of the problem sentences word by word by using the decoder; and (5) training a machine reading understanding model, generating answers according to the question sentences, taking the correct rate of the answers as a rewardfunction, and finely adjusting the question generation model by using reinforcement learning. By utilizing the method and the device, the quality of dialogue type problem generation on a large-scaledata set can be greatly improved.

Description

technical field [0001] The invention belongs to the field of natural language processing, and in particular relates to a dialog question generation method based on reinforced dynamic reasoning. Background technique [0002] The task of conversational question generation is one of the most important and thorny problems in natural language processing. In this task, given an article and an article-based dialogue (question-answer pair), we need to generate a new question to keep the dialogue coherent and related to the article topic. An efficient dialogue question generation model can be widely used in many fields based on semantic understanding, such as intelligent dialogue robots and educational systems, and can also provide data support for the training of intelligent dialogue question answering models. [0003] Question generation and dialog generation, especially generation tasks that use unstructured text data as knowledge sources, have been extensively studied in recent ...

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
IPC IPC(8): G06F16/332G06N3/04
CPCG06N3/049
Inventor 潘博远蔡登李昊
Owner ZHEJIANG 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