Looking for breakthrough ideas for innovation challenges? Try Patsnap Eureka!

Text generation method and system

A text and text sequence technology, applied in the field of text generation methods and systems, can solve problems such as insufficient coding of structural information in knowledge graphs, no explicit modeling graph and text alignment relationship, and achieve optimal performance

Active Publication Date: 2021-07-13
TSINGHUA UNIV
View PDF4 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

Nevertheless, pre-trained language models still face two major challenges when applying knowledge graphs to text generation tasks: 1) Insufficient encoding of the structural information of knowledge graphs; 2) There is no explicit alignment relationship between modeling graphs and texts

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 generation method and system
  • Text generation method and system
  • Text generation method and system

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0047] In order to make the purpose, technical solutions and advantages of the present invention clearer, the technical solutions in the present invention will be clearly and completely described below in conjunction with the accompanying drawings in the present invention. Obviously, the described embodiments are part of the embodiments of the present invention , but not all examples. Based on the embodiments of the present invention, all other embodiments obtained by persons of ordinary skill in the art without creative efforts fall within the protection scope of the present invention.

[0048] figure 1 is a schematic flow chart of the text generation method provided by the present invention, such as figure 1 shown, including:

[0049] S1, obtaining the knowledge map to be input;

[0050] S2. Input the knowledge graph to be input into a text generation framework, and construct an alignment relationship model between the knowledge graph and the output text; wherein the text...

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 provides a text generation method and system. The text generation method comprises: obtaining a to-be-input knowledge graph; inputting the knowledge graph to be input into a text generation framework, and constructing an alignment relationship model of the knowledge graph and an output text, wherein the text generation framework is obtained based on knowledge graph and text joint representation learning. Through the text generation framework based on knowledge graph and text joint representation learning, the explicit alignment relationship between the input graph and the output text can be constructed while knowledge graph structure information is introduced at a coding end, and the optimal performance of an existing model is achieved.

Description

technical field [0001] The present invention relates to the technical field of natural language, in particular to a text generation method and system. Background technique [0002] The knowledge graph is one of the important carriers used by humans to store knowledge in the information age, which describes the entities in the world and the relationship between entities. The knowledge map contains a large amount of structured data, which is often stored in the form of triples. For example, (Beijing, is the capital of..., China) The corresponding text of this triple is "Beijing is the capital of China". [0003] In practical applications, it is usually necessary to convert knowledge graphs into natural language texts, so knowledge graphs to text generation have become one of the classic tasks in the field of natural language processing. With the development of large-scale pre-trained language models in recent years, pre-trained language generation models such as GPT, BART, an...

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): G06F16/36G06F40/279G06F40/30G06N3/04G06N3/08
CPCG06F16/367G06F40/30G06F40/279G06N3/04G06N3/08
Inventor 黄民烈柯沛朱小燕
Owner TSINGHUA UNIV
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Patsnap Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Patsnap Eureka Blog
Learn More
PatSnap group products

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

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap|About US| Contact US: help@patsnap.com