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

Method for performing machine reading understanding by utilizing word vectors with introduced semantic information

A technology for reading comprehension and semantic information, which is applied in the field of machine reading comprehension based on deep learning models to achieve the effect of improving the accuracy rate

Active Publication Date: 2020-11-20
TIANJIN UNIV
View PDF3 Cites 2 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0005] 1) Aiming at the problem of machine reading comprehension, a reading comprehension method that introduces knowledge is proposed to solve the problem of machine reading comprehension more accurately

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
  • Method for performing machine reading understanding by utilizing word vectors with introduced semantic information
  • Method for performing machine reading understanding by utilizing word vectors with introduced semantic information
  • Method for performing machine reading understanding by utilizing word vectors with introduced semantic information

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0078] The present invention adopts Retrofitting technology to fine-tune the word vectors used in the machine reading comprehension model, and introduces the words and the relationship between words in the semantic dictionary into the word vectors. By introducing semantic information, the information loss of the context representation layer is reduced, the processing efficiency of the context-question interaction layer is improved, and the accuracy of the machine reading comprehension model is improved without increasing the complexity of the model. The specific technical solutions are as follows:

[0079] Step 1, embedding: use pre-trained word vectors to represent the context and questions involved in the machine reading comprehension model;

[0080] Step 2, use Retrofitting technology to fine-tune the word vector. Retrofitting is a way to obtain more similar vector representations by encouraging words with mutual relations:

[0081] The detailed process of Retrofitting is: ...

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 belongs to the technical field of natural language automatic processing, aims to solve the problem of machine reading understanding more accurately, and discloses a method for performingmachine reading understanding by using a word vector introduced with semantic information, which comprises the following steps of: 1, expressing the context involved in a machine reading understanding model and words in the problem by using the word vector; 2, performing fine adjustment on the word vector by using Retrofitting to obtain a context sequence and a problem sequence expressed by the word vector; 3, coding: respectively coding the context and the problem sequence to obtain context representation and problem representation; 4, interacting the encoded context with the problem sequence based on iteration; and 5, generating an answer: extracting a starting position and an ending position of an answer fragment from the full-aware context obtained in the step 4. The method is mainlyapplied to machine automatic language processing occasions.

Description

technical field [0001] The invention belongs to the technical field of natural language processing, and in particular relates to a method for realizing machine reading comprehension based on a deep learning model. Background technique [0002] As a method to measure the machine's understanding of text, machine reading comprehension requires the model to answer the questions raised against it according to a given context. This task is one of the standards for measuring the machine's understanding of natural language. The goal of machine reading comprehension is to narrow the gap between machines and humans in natural language understanding. This goal can be formally expressed as: Given a context C, a question Q raised according to C, and a question Q given by humans The correct answer A requires the model to give the correct answer A to the question Q by learning the function F: F(C, Q)=A. Machine reading comprehension is likely to change the way humans and computers interac...

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): G06F16/332G06F16/33G06F16/36G06N3/04
CPCG06F16/3329G06F16/3344G06F16/374G06N3/048G06N3/044G06N3/045
Inventor 魏建国孔维坤
Owner TIANJIN 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