Method for generating abstract based on attention mechanism

A technology of attention and summarization, which is applied in the field of generating summaries based on the attention mechanism, can solve problems such as lack of important information, slow training speed, and difficult training

Active Publication Date: 2020-04-24
HUNAN UNIV
View PDF3 Cites 12 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0005] Aiming at the above defects or improvement needs of the prior art, the present invention provides a method for generating summaries based on attention mechanism, the purpose of which is to solve the problems of slow training speed and training Difficult technical questions, and technical questions that would cause some important information to be missing from the article

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 for generating abstract based on attention mechanism
  • Method for generating abstract based on attention mechanism
  • Method for generating abstract based on attention mechanism

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0088] In order to make the object, technical solution and advantages of the present invention clearer, the present invention will be further described in detail below in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described here are only used to explain the present invention, not to limit the present invention. In addition, the technical features involved in the various embodiments of the present invention described below can be combined with each other as long as they do not constitute a conflict with each other.

[0089] Both the encoder and decoder that generate the summary generative model have their input length set to a fixed value when their input length is set too long. The model will be difficult to train and the model accuracy will drop. A common way to solve this problem is to truncate the part that is longer than the set maximum length, which may cause a part of the complete information of the ...

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 method for generating an abstract based on an attention mechanism to generate a text abstract, which totally comprises two stages: the first stage is a sentence sorting process, the second stage is an abstract generation process, and the input of the abstract generation process is N sentences which are most relevant to an article theme and are obtained through the first stage. In the first stage, a supervised sorting method is provided for articles with titles, firstly, the similarity between each sentence and the title is calculated, then the articles are sorted according to the similarity, and finally N sentences with the highest similarity are selected. For the second stage, the invention proposes a new method for calculating the attention distribution betweenthe encoder and the decoder, i.e. the decoder should pay attention to different parts in the encoder at different times. Through the sorting method and the abstract generation method, the problem of article information attenuation caused by the fact that a part of text must be directly cut off to serve as input of the abstract generation model when the article is too long is relieved.

Description

technical field [0001] The invention belongs to the field of natural language processing, and more specifically relates to a method for generating abstracts based on an attention mechanism. Background technique [0002] With the development of the Internet, network information is growing explosively, how to quickly and effectively obtain network information has become an important research problem. Text summarization was developed under such a background. With the development of information retrieval and natural language processing technology, text summarization has become a research hotspot in recent years. [0003] The purpose of text summarization is to convert a text or a collection of texts into short texts containing key information. According to the input type, text summarization can be divided into single-document summarization and multi-document summarization, where single-document summarization generates summaries from a given document, and multi-document summariz...

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): G06F16/34G06F40/30G06F40/284G06N3/04G06N3/08
CPCG06F16/345G06N3/088G06N3/045
Inventor 唐卓方小泉李肯立周文阳王东周旭刘楚波曹嵘晖
Owner HUNAN 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