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

A machine reading comprehension system based on knowledge map gain

A reading comprehension and knowledge map technology, applied in the field of machine reading comprehension systems, can solve problems such as unsatisfactory output results, achieve the effect of reducing the frequency of occurrence and improving work efficiency

Active Publication Date: 2022-08-09
SHANGHAI UNIVERSITY OF ELECTRIC POWER
View PDF5 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

Then, when the traditional model encounters such documents, it will produce unsatisfactory output results

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 machine reading comprehension system based on knowledge map gain
  • A machine reading comprehension system based on knowledge map gain
  • A machine reading comprehension system based on knowledge map gain

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0016] In order to make the technical means and effects realized by the present invention easy to understand, the present invention will be described in detail below with reference to the embodiments and the accompanying drawings.

[0017]

[0018] figure 1 is a structural block diagram of a machine reading comprehension system based on knowledge graph gain in an embodiment of the present invention, figure 2 It is a schematic flowchart of a machine reading comprehension system based on knowledge graph gain in an embodiment of the present invention.

[0019] like figure 1 and figure 2 As shown, a machine reading comprehension system 100 based on knowledge graph gain in this embodiment is used to receive a text data set including text documents and questions and a vocabulary generated according to the text data set, and according to the text document The content obtains the answer to the question, including: document question arrangement module 10 , named entity recogniti...

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 present invention provides a machine reading comprehension system based on knowledge graph gain, which is used for receiving a text data set including text documents and questions and a vocabulary self-generated according to the text data set, and obtains a question answer according to the content of the text document. Answers, including: Document Question Alignment Module; Named Entity Recognition Module for Named Entity Recognition Processing on Text Datasets; ERNIE Contextual Language Module; External Knowledge Bases, including WordNet Knowledge Base and ConceptNet Knowledge Base, for receiving vocabularies and Correspondingly generate the WordNet knowledge feature vector and the ConceptNet knowledge feature vector; the knowledge matching and connection layer is used to connect the corresponding word vector with the WordNet knowledge feature vector and the ConceptNet knowledge feature vector for the successfully matched entities in the text document and the question; Note The force calculation unit is used to perform bidirectional attention operation and self-attention operation corresponding to each vector to obtain the answer; the result generation unit is used to receive and determine the output answer.

Description

technical field [0001] The invention belongs to the field of artificial intelligence, and in particular relates to a machine reading comprehension system based on knowledge graph gain. Background technique [0002] Machine reading comprehension is a sub-task of natural language understanding. Its goal is to give a text and a question related to the text, and the machine analyzes the text to give the answer to the question. Compared with other traditional natural language processing tasks (such as part-of-speech judgment, entity recognition, grammatical analysis, etc.), machine reading comprehension not only requires machines to learn to represent natural language, but also to understand, analyze, and finally generate output sentences. [0003] The most widespread application of machine reading comprehension is to enhance the performance of human-computer interaction question answering systems. In the most primitive question answering system, the machine just matches the que...

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 Patents(China)
IPC IPC(8): G06F16/36G06F16/332G06F16/953G06F40/295
CPCG06F16/367G06F16/3329G06F16/953G06F40/295
Inventor 徐菲菲张文楷
Owner SHANGHAI UNIVERSITY OF ELECTRIC POWER
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