Automatic problem generation method based on deep learning

A deep learning and automatic generation technology, applied in neural learning methods, biological neural network models, instruments, etc., can solve problems such as incoherent sentences, mismatched content of articles, unreasonable semantics, etc., and achieve the effect of reducing dependence

Pending Publication Date: 2019-04-19
NANJING UNIV OF SCI & TECH
View PDF4 Cites 40 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0008] Existing methods are usually based on rules to implement automatic question generation methods, which rely heavily on manually captured feature sets. T

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
  • Automatic problem generation method based on deep learning
  • Automatic problem generation method based on deep learning
  • Automatic problem generation method based on deep learning

Examples

Experimental program
Comparison scheme
Effect test

Embodiment

[0088] A method for automatically generating questions based on deep learning, comprising the following steps:

[0089] Step 1: Construct training set , verification set , prediction set , note that the answer is a continuous segment in the article: divide the data set by 80%, 10 %, 10% ratio to divide the training set, verification set, and prediction set.

[0090] Step 2: Use the deep learning framework tensorflow to build a sequence-to-sequence neural network model based on encoder-decoder. The model includes attention mechanism, Pointer-Generator Network, Answer-supression mechanism, and attention loss mechanism:

[0091] (1) Encoder-decoder structure based on attention mechanism: There are article encoders and answer encoders in this neural network model, and the encoders are all based on bidirectional LSTM neural networks, and the articles and answers after word segmentation and word embedding Input to article encoder and answer encoder respectively:

[0092]

[009...

Embodiment 2

[0136] combine figure 1 , figure 2 , the implementation process of the present invention is described in detail below, and the steps are as follows:

[0137] Step 1: Build the training set , validation set , prediction set , note that the answer is a continuous segment of the article:

[0138] In the experiment of the present invention, we use two public data sets of SQuAD and DuReader, and divide them into training set, verification set and prediction set according to the ratio of 80%, 10%, and 10%. The specific situation after division is shown in Table 1:

[0139] Table 1: SQuAD, DuReader dataset division

[0140] data set

Article-Answer Pair Quantity (SQuAD)

Number of article-answer pairs (DuReader)

Training set

74345

33780

validation set

9293

4218

prediction set

9534

4225

[0141] Step 2: Use the deep learning framework tensorflow to build a sequence-to-sequence neural network model based on encoder-decoder....

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 discloses an automatic question generation method based on deep learning. The method comprises the following steps: constructing a training set (articles, answers and questions), a verification set (articles, answers and questions) and a prediction set (articles and answers); creating Encoder-based construction by using deep learning framework tensorflow A sequence of decoders to a sequence neural network model; Carrying out word segmentation, word list making and word embedding operations on sentences in the data set; Wherein the data set comprises a training set, a verificationset and a prediction set; The training set is used for training the model, the verification set is used for detecting whether the currently trained model is over-fitted or not, and if over-fitting isachieved, stopping training; Otherwise, continuing training; And decoding the prediction set by using the trained model to generate a problem. The method is good in generalization effect and low in labor cost, the generated questions are better matched with articles and answers, and the method can be widely applied to the fields of intelligent teaching, intelligent questions and answers, knowledge question and answer games and the like.

Description

technical field [0001] The invention belongs to the technical field of natural language processing, and in particular relates to a method for automatically generating questions based on deep learning. Background technique [0002] How to teach machines to better read and understand human language is a big challenge, which requires machines to understand natural language and know some necessary common sense principles. In recent years, research on automatic question generation has become more and more important in the field of natural language. more and more popular. Automatic question generation is to automatically generate high-quality questions related to articles and answers given articles and answers. [0003] The automatic question generation method is a method for automatically generating questions related to articles, which can be widely used in intelligent teaching, intelligent quiz and knowledge quiz games, etc., for example: [0004] Smart education: In the field...

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): G06F16/332G06N3/08G06N3/04
CPCG06N3/049G06N3/08
Inventor 陶冶陆建峰
Owner NANJING UNIV OF SCI & TECH
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