Abstract generation method and apparatus, and computer device

An abstract and generative technology, applied in the field of abstract generation methods, devices and computer equipment, can solve the problems of poor readability and information volume

Active Publication Date: 2018-07-13
TENCENT TECH (SHENZHEN) CO LTD
View PDF8 Cites 45 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0005] In order to solve the problem that the digest generated by the generative model is poor in readability and information when the text sequence length of the document is long, the embodiment of the present invention provides a method, device and computer equipment for generating a digest

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
  • Abstract generation method and apparatus, and computer device
  • Abstract generation method and apparatus, and computer device
  • Abstract generation method and apparatus, and computer device

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0079] In order to make the object, technical solution and advantages of the present invention clearer, the implementation manner of the present invention will be further described in detail below in conjunction with the accompanying drawings.

[0080] figure 1 is a flow chart of a method for generating an abstract provided by an exemplary embodiment of the present invention. The summary generation method includes:

[0081] In step 101, a document D is obtained, and the document D includes at least one sentence.

[0082] In step 102, m candidate sentences are extracted from the document D through the extractive model.

[0083] Optionally, the extractive model includes a model based on an attention mechanism (Attention).

[0084] The model based on the attention mechanism is used to calculate the probability value of each sentence in the document D, and the sentences whose probability value is greater than the preset threshold are extracted as candidate sentences, and the se...

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 an abstract generation method and apparatus, and a computer device, and belongs to the field of natural language processing. The method comprises the steps of obtaining a document D, wherein the document D comprises at least one sentence; extracting m candidate sentences from the document D through an extractive model; and outputting target words according to the m candidate sentences through a generative model, and according to the target words, generating an abstract. Firstly the m candidate sentences suitable to serve as the abstract are extracted through the extractive model, so that the text sequence length needed to be processed by the generative model is reduced; then the target words are generated or extracted according to the m candidate sentences through the generative model; and the abstract of the document is synthesized according to the target words, so that the readability and information quantity of the finally generated abstract are improved.

Description

technical field [0001] The embodiments of the present application relate to the field of natural language processing, and in particular to a method, device and computer equipment for generating an abstract. Background technique [0002] Automatic Text Summarization (Automatic Text Summarization) is used to refine a document to generate a concise, smooth summary that contains the main idea of ​​the article. Automatic text summarization is a major challenge in the field of natural language processing. [0003] The relevant technology provides an automatic text summarization technology based on a generative (Abstractive) model, which is used to extract words from each sentence in a document, and then recombine the extracted words into a sentences to form an abstract. [0004] However, when the text sequence length of the document is long, the words extracted by the generative model are difficult to control, resulting in the final generated summary not meeting the expected res...

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): G06F17/30G06F17/27
CPCG06F16/345G06F40/30G06N3/084G06N3/044G06N3/045G06N7/01
Inventor 孔行
Owner TENCENT TECH (SHENZHEN) CO LTD
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