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

Method and device for reading comprehension based on attention mechanism and electronic device

A technology of reading comprehension and attention, applied in the field of reading comprehension, can solve the problems that restrict the performance of machine reading comprehension system and the industrial application range, and achieve the effect of improving the effect

Active Publication Date: 2018-12-18
北京慧闻科技(集团)有限公司
View PDF2 Cites 37 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

However, in the process of realizing the short text answer extraction based on deep learning, there are still many problems to be overcome. These problems restrict the performance of the machine reading comprehension system and the scope of practical industrial applications.

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 and device for reading comprehension based on attention mechanism and electronic device
  • Method and device for reading comprehension based on attention mechanism and electronic device
  • Method and device for reading comprehension based on attention mechanism and electronic device

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0032] Hereinafter, exemplary embodiments according to the present application will be described in detail with reference to the accompanying drawings. Apparently, the described embodiments are only some of the embodiments of the present application, rather than all the embodiments of the present application, and it should be understood that the present application is not limited by the exemplary embodiments described here.

[0033] Application overview

[0034] As mentioned above, machine reading comprehension (Machine Reading Comprehension, MRC) is an important topic in the field of natural language processing. Its purpose is to allow computers to find accurate answers in massive texts, thereby reducing the cost of human beings to obtain information. Currently, the most popular machine reading comprehension task is the answer extraction task. The reading comprehension task of answer extraction refers to, given a question and a short text (usually within 1000 words) relate...

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

A method and device for reading comprehension based on an attention mechanism and an electronic device are disclosed. The method comprises the following steps: respectively converting the obtained text data and the problem data into word vectors; processing the word vector representations of the problem and the text to obtain the semantic vector representations of the problem and the text respectively; semantically enhancing the semantic vector representation of the problem and the text. The context representation of the fusion problem information is obtained through the attention mechanism layer. The context representation of the fusion problem information is semantically enhanced, and the answer corresponding to the problem data is obtained based on the enhanced context representation ofthe fusion problem information and the enhanced problem semantic vector representation. In this way, the system for machine reading comprehension is optimized through a specific model architecture using semantic enhancement methods to enhance the effectiveness of the short text answer extraction task.

Description

technical field [0001] The present invention generally relates to the field of data processing, in particular to a method, device and electronic equipment for reading comprehension based on an attention mechanism. Background technique [0002] Since the birth of computers, computers have surpassed humans in processing many things, so can computers have intelligence and understand natural language like humans? Machine Reading Comprehension (MRC) is an important topic in the field of natural language processing. Its purpose is to allow computers to find accurate answers in massive texts, thereby reducing the cost of human beings to obtain information. [0003] Machine reading comprehension tasks include cloze tasks, answer extraction tasks, and more complex question-and-answer tasks based on network data. Among them, the most popular reading comprehension task is answer extraction tasks. The reading comprehension task of answer extraction refers to, given a question and a sho...

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): G06F17/27G06F17/30
CPCG06F40/211G06F40/279G06F40/30
Inventor 杨鹏
Owner 北京慧闻科技(集团)有限公司
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