Extractive news digest generating apparatus based on attention encoder

A technology for generating devices and encoders, which is applied in the direction of instruments, biological neural network models, and special data processing applications. It can solve problems such as ignoring relationships and collecting more information in documents, and achieve the effect of accurate extraction.

Active Publication Date: 2019-02-12
NAT UNIV OF DEFENSE TECH
View PDF7 Cites 11 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0003] However, existing encoder-decoder structure-based methods for automatic summarization problems pay too much attention to the decoder part, i.e., these methods usually use the attention mechanism in the decoding part instead of collecting more information about the document in the encoder
Their focus is on obtaining sentences that are more related to the source document, but they ignore the relationship between different sentences

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
  • Extractive news digest generating apparatus based on attention encoder
  • Extractive news digest generating apparatus based on attention encoder
  • Extractive news digest generating apparatus based on attention encoder

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0016] 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 combination with specific embodiments and with reference to the accompanying drawings. It should be understood that these descriptions are exemplary only, and are not intended to limit the scope of the present invention. Also, in the following description, descriptions of well-known structures and techniques are omitted to avoid unnecessarily obscuring the concept of the present invention.

[0017] A schematic diagram of a layer structure according to an embodiment of the invention is shown in the drawing. The figures are not drawn to scale, with certain details exaggerated and possibly omitted for clarity. The shapes of the various regions and layers shown in the figure, as well as their relative sizes and positional relationships are only exemplary, and may deviate due to manufacturing tolerances or techni...

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

An extractive news digest generation apparatus based on an attention encoder includes a statement encoder for acquiring a document and dividing the document into a plurality of sentences; a document encoder for acquiring a document representation according to the relationship between the plurality of sentences and the plurality of sentences; a statement extractor for extracting sentences used as summaries from the plurality of sentences and the document representations. The extractive news digest generation apparatus can capture the relationship and dependency between sentences better, so as to extract abstracts accurately and show more abundant information when generating abstracts.

Description

technical field [0001] The invention relates to the technical field of document abstract extraction, in particular to an extractive news abstract generation device based on an attention encoder. Background technique [0002] With the rapid increase of current news data, the demand for the development of automatic summarization system is becoming more and more urgent. The method of extractive text summarization is to generate a summary by extracting sentences that obviously contain the main information of the document from the document, so that the generated summary is more fluent. The encoder-decoder structure, which has shown great power in solving serialization problems, has been successfully applied to generate extractive summarization, where the encoder reads in the source sentence and represents it with a fixed-length vector, and the decoder outputs the predicted Label, which decides whether to extract a sentence as part of the summary. [0003] However, existing enco...

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): G06F16/34G06F17/24G06F17/27G06N3/04
CPCG06F40/211G06F40/166G06N3/045
Inventor 陈洪辉邵太华蔡飞刘俊先罗爱民郝泽鹏陈皖玉潘志强郭昱普
Owner NAT UNIV OF DEFENSE 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