Machine reading comprehension and method and device for reducing candidate data set size

A technology of reading comprehension and candidate data, which is applied in the field of machine understanding of natural language, can solve problems such as unreasonable sentence patterns and inability to well reflect the natural expression of human thinking logic, and achieve the goal of narrowing the scope, realizing comprehensive prediction, and improving the effect Effect

Active Publication Date: 2021-04-30
深思考人工智能机器人科技(北京)有限公司
View PDF6 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

The generative formula is theoretically not limited by knowledge, and automatically generates answers to questions, but sometimes the answers generated by the generative formula are not the answer to the question, and the sentence structure is unreasonable, which cannot well reflect the characteristics of human thinking logic and natural expression

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 and method and device for reducing candidate data set size
  • Machine reading comprehension and method and device for reducing candidate data set size
  • Machine reading comprehension and method and device for reducing candidate data set size

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0040] In order to make the purpose, technical means and advantages of the present application clearer, the present application will be further described in detail below in conjunction with the accompanying drawings.

[0041] The machine reading comprehension involved in this application, according to the extraction method in machine reading, selects candidate documents from the supporting documents according to the supporting documents and given questions, and extracts or infers the answer corresponding to the given questions from the candidate documents. The difference in the form and quantity of supporting documents makes the data sets (divided by function, including problem sets, training sets, development sets, and test sets) different, the algorithm models adopted are also different, and the operating efficiency of the algorithm models is also different. For example, the supporting document of the Stanford dataset is directly the most relevant paragraph, while the MS MARC...

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

Disclosed is an implementation method of machine reading comprehension, filtering the first data set according to the question type to obtain the filtered second data set; performing semantic matching between the question and the data i in the second data set to obtain the semantic matching score of the data i; Calculate the maximum coverage of the question and the data i to obtain the feature matching score of the data i; weight the semantic matching score and feature matching score of the data i to obtain the matching score of the question and the data i; calculate the data i according to the multi-document voting algorithm The voting score of data i, according to the matching score and voting score of data i, calculate the final score of data i; select the first n data in the sequence according to the descending order of the final score as the candidate data set; input the candidate data set into the baseline The model predicts the answer of the input data set based on the baseline model, and obtains a candidate answer set for the question. This application implements the sorting of data sets and extracts effective answers to questions.

Description

technical field [0001] The present invention relates to machine comprehension of natural language, in particular, to a method and device for realizing machine reading comprehension. Background technique [0002] With the rise and development of the Internet, data has grown rapidly. How to use machine reading comprehension technology to help users find satisfactory answers is a classic topic in the field of natural language understanding technology research. As a sub-field of natural language understanding, machine reading comprehension has always been the focus of researchers and the industry, and it is also the core problem of intelligent voice interaction and human-computer dialogue. Machine reading comprehension (Machine Reading Comprehension) is to allow machines to read natural language texts like humans, and then summarize them through reasoning, so that they can accurately answer questions related to the reading content. [0003] Machine reading methods fall into two...

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): G06F16/33
Inventor 杨志明时迎成
Owner 深思考人工智能机器人科技(北京)有限公司
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