Method and system for searching whether-class problem key sentences in reading understanding task

A technology for reading comprehension and key sentences, applied in the field of natural language data processing, can solve the problems of poor scalability, low correct rate, and inability to find key information in traditional methods, and achieve the goals of reducing manual annotation, improving correct rate, and improving answer efficiency Effect

Inactive Publication Date: 2020-08-18
AEROSPACE INFORMATION RES INST CAS
View PDF6 Cites 6 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0004] In order to solve the problem that the accuracy rate of the existing traditional rule method is too low when searching for key sentences related to the question, the model cannot find the key information matching the question when answering the question, and the scalability of the traditional method is poor. Limitations of the Sentence Query Domain

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 system for searching whether-class problem key sentences in reading understanding task
  • Method and system for searching whether-class problem key sentences in reading understanding task
  • Method and system for searching whether-class problem key sentences in reading understanding task

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0053] Such as figure 1 Shown, the present invention provides a kind of whether class problem key sentence search method in the reading comprehension task, carries out according to the following steps:

[0054] S1 selects the existing reading comprehension question and answer data, preprocesses the question and answer data to obtain a data set, and then divides the data set into a training set, a verification set and a test set;

[0055] S2 is based on the constructed coding layer network, mining the semantic information of the sentences in the question sentences and discourse paragraphs in the training set and test set, and obtaining the word embedding representation of each word in the sentence;

[0056] S3 builds an algorithm model, and uses the neural network model and TFIDF to calculate the key sentences of whether or not questions from the questions and paragraphs mined through the coding layer network;

[0057] S4 Input the data of the question-and-answer for reading c...

Embodiment 2

[0090] Given a question and a sentence, is Beijing the capital of China? Beijing is the capital of China

[0091] Participle:

[0092] Send it into the model, and get the word embedding representation through the neural network and TF-IDF

[0093] Calculate the cosine similarity between questions and discourse paragraphs

[0094] Return the result, the sentence is the key sentence of the question

[0095] Given a question and a sentence, is Beijing the capital of China? Winter vacation extended to November this year

[0096] Word segmentation:

[0097] Send it into the model, and get the word embedding representation through the neural network and TF-IDF

[0098] Calculate the cosine similarity between questions and discourse paragraphs

[0099] Return the result, the sentence is not a question key sentence

[0100] Furthermore, the model update can choose automatic update and upgrade or manual one-click update and upgrade.

Embodiment 3

[0102] In order to realize the above-mentioned method, the present invention also proposes a system for finding key sentences of whether or not questions in the reading comprehension task, including as shown in the figure:

[0103] The data preparation module is used to select existing reading comprehension question and answer data, preprocess the question and answer data to obtain a data set, and then divide the data set into a training set, a verification set and a test set;

[0104] Word and sentence encoding module, which is used to mine the semantic information of sentences in question sentences and discourse paragraphs in the training set and test set based on the constructed encoding layer network, and obtain the word embedding representation of each word in the sentence;

[0105] The key sentence matching module is used to use the neural network model and TFIDF to calculate the key sentence of whether the questions and paragraphs are mined through the coding layer netwo...

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 provides a method and a system for searching whether-class problem key sentences in a reading understanding task. The method comprises the steps of selecting existing reading understanding question and answer data, preprocessing the question and answer data to obtain a data set, and then mining semantic information of questions and sentences in chapter paragraphs in the data set based on a coding layer network to obtain word embedding representation of each word; constructing an algorithm model, and calculating the questions and the text paragraphs mined through the coding layernetwork by using a neural network model and a TFIDF to obtain key sentences of whether problems are classified or not; and inputting to-be-read understanding question and answer data into the trainedalgorithm model, and predicting whether key sentences of questions are classified or not. According to the method, more key sentence supports can be provided, the weight of the key sentence is calculated through the combination of the bidirectional gating loop network and the TF-IDF, and the efficiency and accuracy of answering the whether-class problems are improved.

Description

technical field [0001] The invention belongs to the technical field of processing natural language data, and in particular relates to a method and system for finding key sentences of whether or not questions in reading comprehension tasks. Background technique [0002] With the explosive growth of network information, all kinds of information flood the entire network environment. People are now used to go to the Internet to search for some solutions to problems. When users are not very familiar with some search techniques, they often need to spend a lot of time to filter the results returned by the search engine. The birth of the reading comprehension system has effectively solved the problem of complicated information mentioned above. The reading comprehension system uses natural language processing to analyze the questions submitted by users, obtain relevant answers and return them to users. [0003] The search for the key sentences of whether or not questions has alway...

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 Applications(China)
IPC IPC(8): G06F16/33G06F40/30G06F40/211G06N3/04
CPCG06F16/3344G06F40/30G06F40/211G06N3/045
Inventor 许光銮于泓峰孙显田雨姚方龙李沛光吴红莉刘那与
Owner AEROSPACE INFORMATION RES INST CAS
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