Eureka AIR delivers breakthrough ideas for toughest innovation challenges, trusted by R&D personnel around the world.

Viewpoint type problem reading understanding method based on multilayer bidirectional LSTM and verification model

A technology for verifying models and reading comprehension, applied in the field of machine learning, can solve problems such as poor comprehension and reasoning ability, poor performance, and strong subjectivity, and achieve high accuracy and precise selection

Active Publication Date: 2019-06-25
海南中智信信息技术有限公司
View PDF3 Cites 12 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0002] The characteristic of reading comprehension of opinion-type questions is that, given a question and an article, the correct answer is obtained by using the information of multiple sentences in the article. The existing technology usually models the entire article, and uses the neural network model from Extract the paragraphs related to the given question from the article, extract candidate answers from them, and then get the correct answer from the candidate answers. However, there is an important strong assumption in the learning process of such methods, that is, in a given article There are always candidate answers in , which will make it impossible to get the correct answer when dealing with questions that are highly subjective and have no clear answer. Not good, and will affect the performance of the entire opinion-type question reading comprehension system, making it show poor comprehension and reasoning skills

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
  • Viewpoint type problem reading understanding method based on multilayer bidirectional LSTM and verification model
  • Viewpoint type problem reading understanding method based on multilayer bidirectional LSTM and verification model
  • Viewpoint type problem reading understanding method based on multilayer bidirectional LSTM and verification model

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0032] The principles and features of the present invention will be described below in conjunction with the accompanying drawings, and the enumerated embodiments are only used to explain the present invention, and are not intended to limit the scope of the present invention.

[0033] The present invention provides a multi-layer bidirectional LSTM and a method for reading comprehension of viewpoint-type questions of a verification model, and the method specifically includes the following steps:

[0034] S1. Preprocessing the sentences in articles and questions, the preprocessing includes word segmentation, part-of-speech tagging, named entity recognition, mapping words into corresponding word vectors in the vocabulary, and splicing them with feature vectors of part-of-speech and named entity types Together, form the initial feature vector representations of articles and questions.

[0035] S2. The initial feature vector representations of articles and questions are respectively...

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 a viewpoint type problem reading understanding method based on a multilayer bidirectional LSTM and a verification model. According to the method, the advantages of an extraction type model and a judgment type model are fused. Based on reading understanding and feature learning, inference modeling is added, to obtain rational feature representation of a problem and an article, and the relationship between the candidate answers and the correct answers is used as a classification question in subsequent learning. A corresponding Loss function is designed, a verification model is designed for the situation that a part of questions cannot obtain correct answers in a given article, and compared with an existing method, the method is higher in accuracy when the viewpoint type problem reading understanding data set is processed.

Description

technical field [0001] The invention relates to the technical field of machine learning, in particular to a reading comprehension method for opinion-type questions based on a multi-layer bidirectional LSTM and a verification model. Background technique [0002] The characteristic of reading comprehension of opinion-type questions is that, given a question and an article, the correct answer is obtained by using the information of multiple sentences in the article. The existing technology usually models the entire article, and uses the neural network model from Extract the paragraphs related to the given question from the article, extract candidate answers from them, and then get the correct answer from the candidate answers. However, there is an important strong assumption in the learning process of such methods, that is, in a given article There are always candidate answers in , which will make it impossible to get the correct answer when dealing with questions that are high...

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): G06F17/27G06N3/04G06N5/04
Inventor 吴嘉琪于建港肖定和
Owner 海南中智信信息技术有限公司
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
Eureka Blog
Learn More
PatSnap group products