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

Machine reading comprehension method based on multi-task joint training, and computer storage medium

A reading comprehension, multi-tasking technology, applied in the field of machine reading comprehension methods and computer storage media, can solve the problem of low accuracy of Chinese text, and achieve the effect of accelerating training, improving stability and accuracy

Active Publication Date: 2019-10-08
THE 28TH RES INST OF CHINA ELECTRONICS TECH GROUP CORP
View PDF8 Cites 19 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0004] Purpose of the invention: The present invention aims to provide a machine reading comprehension method and computer storage medium suitable for Chinese, aiming to solve the problems of low accuracy of Chinese texts in existing machine reading comprehension methods

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 comprehension method based on multi-task joint training, and computer storage medium

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0035] The present invention will be further explained below in conjunction with the accompanying drawings and specific embodiments.

[0036] like figure 1 As shown, a machine reading comprehension method based on multi-task joint training, including model construction and training phase, testing phase;

[0037] The model building and training phase includes the following steps:

[0038] Step 1. Construct a training set, including the following steps:

[0039] (1.1) collect training corpus, described training corpus comprises article, based on the question of article, the answer of question;

[0040] (1.2) Preprocessing the training corpus, the preprocessing includes: converting traditional Chinese characters into simplified characters, converting full-width numbers and full-width letters into half-width numbers and half-width letters, removing the first punctuation mark of the answer, and removing the question in the training corpus as empty Or the corpus with empty articl...

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 machine reading comprehension method based on multi-task joint training, and a computer storage medium. The machine reading comprehension method comprises a model construction and training stage and a test stage, wherein the model construction and training stage comprises the following steps: 1, constructing a training set; 2, establishing a machine reading comprehensionmodel which comprises a coding layer, an attention matching layer and a decoding layer; 3, dividing the training set into W sub-sample sets according to the number of samples, and training the machinereading comprehension model by using the W sub-sample sets to obtain W machine reading comprehension models; and the testing stage comprises the steps: cutting off a to-be-tested article, inputting the processed article and questions into the trained W machine reading comprehension models, obtaining W predicted answer starting positions, W predicted answer ending positions and W corresponding distribution probabilities, and calculating the average value to serve as the starting position, the ending position and the corresponding distribution probabilities of a final answer. The machine reading comprehension method can solve the problems that an existing machine reading comprehension method is low in Chinese text accuracy and the like.

Description

technical field [0001] The invention belongs to the technical field of machine learning, and in particular relates to a machine reading comprehension method and a computer storage medium. Background technique [0002] Allowing machines to complete reading comprehension and question answering is a hot topic at the forefront of the current AI field, mainly involving deep learning, natural language processing and information retrieval. Machine reading comprehension has high research value in both industry and academia. It enables computers to help humans find the answers they want in a large amount of text, thereby reducing the cost of people's access to information. Perhaps, the future search engine will not only return user-related links and web pages, but will directly return the answer to the user by reading and comprehending the massive resources on the Internet. [0003] At present, the reading comprehension task based on extraction is relatively mature, and the reading ...

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): G06F16/35G06K9/62
CPCG06F16/35G06F18/2411G06F18/214
Inventor 徐建吴蔚王鑫鹏徐琳李晓冬王羽王冬冬
Owner THE 28TH RES INST OF CHINA ELECTRONICS TECH GROUP CORP
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