Text abstract automatic generation method based on self-attention network

An automatic generation and attention technology, applied in biological neural network models, unstructured text data retrieval, text database browsing/visualization, etc. Improve quality, high-quality effects

Active Publication Date: 2019-09-06
SOUTH CHINA UNIV OF TECH
View PDF10 Cites 47 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

Therefore, the automatic generation of text summaries through the above methods has...

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
  • Text abstract automatic generation method based on self-attention network
  • Text abstract automatic generation method based on self-attention network
  • Text abstract automatic generation method based on self-attention network

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0035] The present invention will be further described below in conjunction with specific examples.

[0036] In the method for automatically generating a text summary based on a self-attention network provided in this embodiment, a piece of text is input for generation. The complete process of generating the summary is as follows figure 1 As shown, the complete neural network structure of the designed text summary automatic generation is as follows Figure 5 shown. When preprocessing the input text, use the word segmentation algorithm to divide the text to be processed into semantically independent words, and fill in empty characters or truncate them depending on the length of the input text; then, according to the word embedding algorithm, the word sequence of the input text The words in correspond to corresponding word vector sequences one by one; next, the encoder is used to encode the word vector sequence of the input text; finally, the decoder is used to perform cyclic ...

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 text abstract automatic generation method based on a self-attention network. The text abstract automatic generation method comprises the following steps: 1) carrying out wordsegmentation on an input text to obtain a word sequence; 2) performing word embedding on the word sequence to generate a corresponding word vector sequence; 3) coding the word vector sequence by using a self-attention network encoder, and 4) decoding an input text coding vector by using a self-attention network decoder to generate a text abstract. The text abstract automatic generation method hasthe advantages of high model calculation speed, high training efficiency, high generated abstract quality, good generalization performance of the model and the like.

Description

technical field [0001] The present invention relates to the technical field of natural language processing, in particular to a method for automatically generating text abstracts based on a self-attention network. Background technique [0002] Text summary refers to one or a paragraph of sentences extracted and summarized from the source text, which can fully reflect the main idea of ​​the text, and is concise and easy to read. Automatic generation of text summaries refers to the technology of using computers to automatically generate text summaries. The goal of automatic text summaries is to use computer science and natural language processing technology to extract important content from the original text, and then extract the important content of the text according to the user's The required form is re-presented to the user. [0003] Existing models for automatically generating text summaries include sequence-to-sequence models based on recurrent neural networks, combinati...

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): G06F16/34G06F17/27G06N3/04
CPCG06F16/345G06N3/04G06F40/284G06F40/289G06N3/045
Inventor 张宇郑冬云郭炜强郑波关健创
Owner SOUTH CHINA UNIV OF 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