Machine reading understanding method, system and device based on deep learning and medium

A reading comprehension and deep learning technology, applied in the field of computer natural language processing and automatic question answering system research, can solve problems such as not fully considering the impact of answer types on the final answer selection, machine reading comprehension models not making full use of question types, etc., to achieve Efficient answer extraction strategy, reducing search space and time, and improving accuracy

Active Publication Date: 2020-01-14
JINAN UNIVERSITY
View PDF9 Cites 33 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0009] 1) The existing question-and-answer machine reading comprehension model does not make full use of the question type, nor does it fully consider the impact of the answer type on the final answer selection
[0010] 2) Most of the existin

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
  • Machine reading understanding method, system and device based on deep learning and medium
  • Machine reading understanding method, system and device based on deep learning and medium
  • Machine reading understanding method, system and device based on deep learning and medium

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0084] like figure 1 and figure 2 As shown, the present embodiment provides a deep learning-based machine reading comprehension method, the method comprising the following steps:

[0085] S101. Construct a question classification model and support a sentence search model and an answer determination model.

[0086] like image 3 As shown, the problem classification model of this embodiment is implemented based on a convolutional neural network (Convolutional Neural Network, referred to as CNN) model, and the convolutional neural network model includes an input layer, a convolutional layer, a pooling layer, a merging layer, and a first layer connected in sequence. Fully connected layer, second fully connected layer and Softmax layer.

[0087] like image 3 and Figure 4 As shown, construct a problem classification model, specifically including:

[0088] S401. Obtain a question classification model training set.

[0089] The question classification model training set in t...

Embodiment 3

[0201] Such as Figure 10 As shown, the present embodiment provides a machine reading comprehension system based on deep learning. The system includes a building block 1001, a question type prediction module 1002, a supporting sentence prediction module 1003 and an answer prediction module 1004. The specific functions of each module are as follows:

[0202] The construction module 1001 is used to construct a question classification model, a supporting sentence search model and an answer determination model.

[0203] The question type prediction module 1002 is configured to input the target question into the question classification model, perform prediction through the question classification model, and output the target question type.

[0204] The supporting sentence prediction module 1003 is used to input the target question and an article to be read and comprehend into the supporting sentence search model, perform prediction through the supporting sentence search model, and ...

Embodiment 4

[0208] This embodiment provides a computer device, which can be a computer, such as Figure 11 As shown, a processor 1102, a memory, an input device 1103, a display 1104 and a network interface 1105 are connected through a system bus 1101, the processor is used to provide calculation and control capabilities, and the memory includes a non-volatile storage medium 1106 and an internal memory 1107, the non-volatile storage medium 1106 stores an operating system, a computer program, and a database, the internal memory 1107 provides an environment for the operation of the operating system and the computer program in the non-volatile storage medium, and the processor 1102 executes the During computer program, realize the machine reading comprehension method of above-mentioned embodiment 1, as follows:

[0209] Build a question classification model, support sentence search model and answer determination model;

[0210] Input the target problem into the problem classification model, ...

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 deep learning-based machine reading understanding method, system and device, and a medium. The method comprises the steps of constructing a question classification model, a support sentence search model and an answer determination model; inputting the target problem into a problem classification model, predicting through the problem classification model, and outputting toobtain a target problem type; inputting the target question and a to-be-read understanding article into a support sentence search model, predicting through the support sentence search model, and outputting to obtain a support sentence sequence related to the answer of the target question; and inputting the target question, the answer type corresponding to the target question type and the supportsentence sequence related to the answer of the target question into an answer determination model, performing prediction through the answer determination model, and performing output to obtain the answer of the target question. The method is suitable for English machine reading understanding tasks, can effectively process the situation that many article paragraphs exist and answers can be obtainedonly by reasoning in multiple paragraphs, and improves the accuracy of machine reading understanding.

Description

technical field [0001] The invention relates to a machine reading comprehension method, system, device and medium based on deep learning, and belongs to the research field of computer natural language processing and automatic question answering system. Background technique [0002] Machine reading comprehension hopes that the machine can "understand" the content of the article like a human being, make reasonable reasoning, and answer relevant questions. It has a wide range of application values ​​and has achieved some results. For example, Baidu's smart speaker "Xiaodu" can basically communicate with people in a simple way, and can issue simple commands (set the alarm clock, check the weather, automatically play the song name, etc.); Eleven shopping activities solve the confusion of most users and help them understand the rules of shopping activities. In addition, machine reading comprehension technology can also be developed and used in various specific fields, becoming a ...

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): G06F16/36G06F16/35
CPCG06F16/36G06F16/353G06F16/355
Inventor 刘波付伟
Owner JINAN UNIVERSITY
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