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

A method and device for training a summary generation model

A technology for generating models and summaries, applied in the field of deep learning, to reduce the problem of word repetition, improve performance, and increase coherence and readability

Active Publication Date: 2020-09-01
JINGDONG TECH HLDG CO LTD
View PDF3 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0004] Existing technologies can use neural networks to automatically generate summaries, so it is prone to the problem of repeatedly generating a sentence or a word

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
  • A method and device for training a summary generation model
  • A method and device for training a summary generation model
  • A method and device for training a summary generation model

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0085] The exemplary embodiments of the present invention are described below in conjunction with the accompanying drawings, which include various details of the embodiments of the present invention to facilitate understanding, and they should be considered as exemplary only. Accordingly, those of ordinary skill in the art will recognize that various changes and modifications of the embodiments described herein can be made without departing from the scope and spirit of the invention. Also, descriptions of well-known functions and constructions are omitted in the following description for clarity and conciseness.

[0086] figure 1 is a schematic diagram of the main flow of the method for training a summary generation model according to an embodiment of the present invention, such as figure 1 As shown, the method for training a summary generation model according to an embodiment of the present invention includes steps S101, S102, S103, S104, S105 and S106.

[0087] S101: Gener...

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 and device for training an abstract generation model, and relates to the technical field of deep learning. A specific embodiment of the method includes: according to the preprocessed data, generating a word-level vector, the first coded hidden layer state and the first hidden layer state; according to the word-level vector, the first coded hidden layer state and the first hidden layer state state, calculate the first attention metric; according to the first attention metric, calculate the first context vector; according to the first context vector, generate the sentence-level vector, the second coding hidden layer state and the second hidden layer state; according to the sentence-level vector , the second encoding hidden layer state and the second hidden layer state, calculating a second attention measure and performing similarity processing; and performing additional processing and generating a summary. This embodiment overcomes the problem of repetition of words and sentences caused by the traditional summary generation model.

Description

technical field [0001] The present invention relates to the technical field of deep learning, in particular to a method and device for training a summary generation model. Background technique [0002] Abstract generation refers to the use of natural language processing technology to analyze and process one or more paragraphs of text, and automatically summarize and generate abstracts, so that readers can spend less time understanding the general content of this paragraph or multiple paragraphs of text without having to read the full text. This technology can be combined with text classification, text keyword extraction and other technologies, and applied in intelligent text analysis system, intelligent office assistant, intelligent news release system and other fields. The current automatic summary generation technology is mainly divided into two categories: TextRank-based extractive automatic summary generation and deep learning-based generative automatic summary generatio...

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 Patents(China)
IPC IPC(8): G06F16/34G06F40/289G06N3/04G06N3/08
CPCG06N3/08G06F40/289G06N3/044G06N3/045
Inventor 闫然王虎
Owner JINGDONG TECH HLDG CO LTD
Features
  • R&D
  • Intellectual Property
  • Life Sciences
  • Materials
  • Tech Scout
Why Patsnap Eureka
  • Unparalleled Data Quality
  • Higher Quality Content
  • 60% Fewer Hallucinations
Social media
Patsnap Eureka Blog
Learn More

Browse by: Latest US Patents, China's latest patents, Technical Efficacy Thesaurus, Application Domain, Technology Topic, Popular Technical Reports.

© 2025 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap|About US| Contact US: help@patsnap.com