Article generation method and device

An article and module generation technology, applied in neural learning methods, character and pattern recognition, biological neural network models, etc., can solve the problems of redundant information, failure to take into account, poor quality of long text content, etc., to improve content quality , improve relevance, intelligence and the effect of natural human-computer interaction

Active Publication Date: 2020-01-17
BEIJING KINGSOFT DIGITAL ENTERTAINMENT CO LTD +1
View PDF31 Cites 3 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0003] In the existing text generation method, the text is generated according to the information input by the user, and the vector-level feature expression is obtained by encoding the input information at one time, and then the encoding result is decoded to generate the text. The above encoding and decoding process is only performed once, and the generated The sentence does not take into account the information of the previous sentence, and the quality is better when generating sentence-level text with a small number of words, but for long texts such as paragraphs or articles containing hundreds or thousands of words, the generated long text will appear In the case of a large number of repeated sentences, there is more redundant information, and the quality of the generated long text content is poor

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
  • Article generation method and device
  • Article generation method and device
  • Article generation method and device

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0025] In the following description, numerous specific details are set forth in order to provide a thorough understanding of the application. However, the present application can be implemented in many other ways different from those described here, and those skilled in the art can make similar promotions without violating the connotation of the present application. Therefore, the present application is not limited by the specific implementation disclosed below.

[0026] Terms used in one or more embodiments of this specification are for the purpose of describing specific embodiments only, and are not intended to limit one or more embodiments of this specification. As used in one or more embodiments of this specification and the appended claims, the singular forms "a", "the", and "the" are also intended to include the plural forms unless the context clearly dictates otherwise. It should also be understood that the term "and / or" used in one or more embodiments of the present sp...

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 an article generation method and device. The article generation method comprises the steps: receiving a title text, and determining an entity relation in the title text; generating a first sentence according to the title text, the entity relationship and the initiator; generating an i-th sentence according to the title text, the entity relationship and an i-1-th sentence until a generation condition is met, where i is greater than or equal to 2; and splicing the generated sentences to obtain an article. According to the article generation method, the phenomenon of repeated sentences in the article is avoided, and the relevance between the generated ith sentence and the title text and the relevance between the generated ith sentence and the entity relationship are improved according to the information of the title text and the entity relationship during generation of the ith sentence, and it is ensured that the generated ith sentence is associated with the information of the title text, and the content quality in the generated article is greatly improved.

Description

technical field [0001] The present application relates to the technical field of natural language processing, in particular to a method and device for generating an article, a computing device, and a computer-readable storage medium. Background technique [0002] Automatic text generation is an important research direction in the field of natural language processing, and the realization of automatic text generation is also an important sign of the maturity of artificial intelligence. Automatic text generation includes text-to-text generation. Text-to-text generation technology mainly refers to the technology of transforming and processing a given text to obtain new text. Automatic text generation technology can be applied to systems such as intelligent question answering and dialogue, machine translation, etc. Realize more intelligent and natural human-computer interaction. [0003] In the existing text generation method, the text is generated according to the information i...

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): G06F40/30G06F40/295G06K9/62G06N3/04G06N3/08
CPCG06N3/08G06N3/044G06N3/045G06F18/241Y02D10/00
Inventor 杨光磊廖敏鹏李长亮
Owner BEIJING KINGSOFT DIGITAL ENTERTAINMENT 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