A method for answering multiple choice questions in reading comprehension based on data augmentation

A technology for reading comprehension and multiple-choice questions, which is applied in the field of answering multiple-choice questions for reading comprehension based on data enhancement. The effect of the dataset

Active Publication Date: 2022-05-27
SHANXI UNIV
View PDF9 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0007] At present, there are relatively few data enhancement methods proposed for machine reading comprehension, and there are no relevant literature introductions for data enhancement methods specifically for reading comprehension multiple-choice questions.

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
  • A method for answering multiple choice questions in reading comprehension based on data augmentation
  • A method for answering multiple choice questions in reading comprehension based on data augmentation
  • A method for answering multiple choice questions in reading comprehension based on data augmentation

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0058] The specific embodiments of the present invention will be further described in detail below with reference to the accompanying drawings.

[0059] like figure 1 As shown, a method for answering multiple-choice questions in reading comprehension based on data enhancement includes the following steps:

[0060] S1. Use the sliding window method to crop the background material of multiple choice questions for reading comprehension;

[0061] S2. Standardize the background material, question stem and option data format of multiple-choice reading comprehension questions;

[0062] S3. Use the TF-IDF method to extract candidate sentences for answering questions from the perspective of word frequency, and obtain a sentence set X of answering materials;

[0063] S4. Use Bi-Attention to extract candidate sentences for answering questions from the perspective of high-dimensional sentence vectors, and obtain a sentence set X of answering materials;

[0064] S5. Merge the sentence ...

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 relates to the field of natural language processing, in particular to a method for answering multiple choice questions for reading comprehension based on data enhancement. The method is: using the sliding window method to cut the background material of the reading comprehension multiple-choice question; standardizing the background material, question stem and option data format of the reading comprehension multiple-choice question; Sentence set X; use Bi‑Attention to extract candidate sentences from the perspective of high-dimensional sentence vectors to obtain answer material sentence set X; combine the sentence sets X and Y obtained by deduplication S3 and S4 to obtain candidate sentence set Z; The EDA strategy for multiple-choice questions expands the candidate sentence set Z to obtain the final data-enhanced candidate sentence set; the final data-enhanced candidate sentence set is input to the BERT model for reading comprehension multiple-choice question answer prediction.

Description

technical field [0001] The invention relates to the field of natural language processing, in particular to a method for answering multiple-choice questions of reading comprehension based on data enhancement. Background technique [0002] In recent years, the task of machine reading comprehension has received extensive attention from scholars in the field of natural language processing at home and abroad, and has become one of the core tasks for evaluating intelligent systems based on natural language comprehension. [0003] Machine reading comprehension mainly includes multiple-choice questions and subjective questions. Among them, reading comprehension multiple-choice questions are further divided into textual comprehension and fragment comprehension multiple-choice questions. The two aim to select the best answer from multiple options based on the "understanding" of the background material. Long and key information is extremely hidden, and the answer cannot be found direc...

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): G06F40/216G06F40/279G06F40/289
CPCG06F40/216G06F40/279G06F40/289
Inventor 张虎张颖雷登斌潘邦泽杨陟卓李茹
Owner SHANXI UNIV
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