Unlock instant, AI-driven research and patent intelligence for your innovation.

Text abstract generation method based on topic enhancement

A text and topic technology, which is applied in the field of text summary generation based on topic enhancement, can solve problems such as repeated words and sentences, and text summary is not smooth, and achieve the effect of simple operation, simple principle, and improvement of topic relevance and sentence quality

Pending Publication Date: 2020-10-16
HUNAN UNIV
View PDF2 Cites 2 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

Generative text summarization uses machine learning to train and generate sentences that are different from the source text, without adding grammatical information, resulting in problems such as incoherence and repetitive words and sentences in the generated text summaries

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 generation method based on topic enhancement
  • Text abstract generation method based on topic enhancement
  • Text abstract generation method based on topic enhancement

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0036] The present invention will be further described in detail below in conjunction with the accompanying drawings and specific embodiments.

[0037] The text abstract generation method based on topic enhancement of the present invention is based on the Seq2seq model, introduces a topic module and a text abstract generation method of a double-attention mechanism, and then proposes a topic-related text abstract based on a double-attention mechanism Automatic generation model (Topic Attention Text Summarization Generation, TA-TSG). This model adds a topic information module based on the Seq2seq model. In order to improve the topic relevance and sentence quality of the content generated by text summarization, this model adopts a new attention mechanism, that is, a double attention mechanism combining keyword-weighted topic attention mechanism and text information attention mechanism.

[0038] like figure 1 and figure 2 As shown, the text summary generation method based on t...

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 generation method based on topic enhancement. The text abstract generation method comprises the steps of S1 performing compression encoding on a text and then inputting the text; S2 combining the topic information with the source text information, and forming text information through a double attention mechanism, wherein the double attention mechanism comprises a topic attention module and a text attention module; and S3 decoding the text information formed in the step S2, and generating a text abstract related to the source text content and enhanced intopic information. The method has the advantages of being simple in principle, easy and convenient to operate, capable of greatly improving topic correlation and statement quality of text abstract generation content and the like.

Description

technical field [0001] The invention mainly relates to the technical field of text data processing, in particular to a method for generating text summaries based on topic enhancement. Background technique [0002] With the rapid development of the Internet, online social media such as Weibo, Moments, and Facebook have become widely popular, and original content push platforms such as Toutiao and Official Accounts have risen strongly. People are increasingly relying on online channels to obtain the information they need. However, the rapid development of the Internet and the rise of various mobile terminal devices have resulted in an explosive growth of text information in the network. However, today's fast-paced lifestyle makes people only use fragmented time to obtain useful information from massive amounts of information. Therefore, how to enable people to quickly and accurately obtain valuable information from the complicated text information within an effective time is ...

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): G06F16/35G06F40/284G06N3/04
CPCG06F16/35G06F40/284G06N3/049G06N3/044
Inventor 赵欢李婷婷李祎颖
Owner HUNAN UNIV