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

A text sequence generation method, device, equipment and medium

A text sequence and sequence technology, applied in the field of artificial intelligence, can solve problems such as unsmoothness, factual errors or omissions, and blunt text articles, and achieve the effect of improving accuracy and fluency

Active Publication Date: 2022-03-04
BEIJING BYTEDANCE NETWORK TECH CO LTD
View PDF15 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0004] However, the existing text conversion technology may have factual errors or omissions, and the text articles obtained after conversion are generally stiff and not smooth

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 text sequence generation method, device, equipment and medium
  • A text sequence generation method, device, equipment and medium
  • A text sequence generation method, device, equipment and medium

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0042] figure 1 It is a flow chart of a method for generating a text sequence provided by Embodiment 1 of the present disclosure. The method is applicable to various text editing scenarios and generates a new text sequence based on an existing text sequence. The method is executed by a device for generating a text sequence, which device can be realized by means of software and / or hardware, and can be specifically inherited in an electronic device with storage and computing capabilities for text processing.

[0043] Such as figure 1 As shown, a method for generating a text sequence is provided, including:

[0044] Step 110, obtaining an initial text sequence, and extracting initial text features from the initial text sequence;

[0045] The initial text sequence is an existing text sequence, which is equivalent to the source text sequence and is used to generate a new target text sequence. The initial text sequence can be an independent sentence including several or more than...

Embodiment 2

[0062] Figure 2A It is a flowchart of a method for generating a text sequence provided in Embodiment 2 of the present disclosure. The technical solution of this embodiment is further refined on the basis of the above-mentioned technical solution, and specifically mainly includes the following steps:

[0063] Step 210, obtaining an initial text sequence, and extracting initial text features from the initial text sequence;

[0064] Step 220, acquiring a structured text sequence, and extracting structured features from the structured text sequence; wherein, the structured text sequence is associated with facts in the initial text sequence;

[0065] Step 230: Filter the initial text features according to the structured features, and correct the text content of the initial text features according to the structured features, so as to fuse and generate the target text sequence;

[0066] The facts embodied in the structured text sequence are generally more accurate and refined, whi...

Embodiment 3

[0072] image 3 It is a flow chart of a text sequence generation method provided by Embodiment 3 of the present disclosure. This embodiment is based on the foregoing embodiments, and further introduces an implementation manner of generating a target text sequence based on fusion of initial text features and structured features. The method includes:

[0073] Step 310, obtaining an initial text sequence, and extracting initial text features from the initial text sequence;

[0074] Step 320, acquiring a structured text sequence, and extracting structured features from the structured text sequence; wherein, the structured text sequence is associated with facts in the initial text sequence;

[0075] Step 330, taking each initial text feature as the current initial text feature;

[0076] This embodiment can process the serialized initial text features one by one. For example, an existing article actually includes multiple initial text sequences in order, and the initial text feat...

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 embodiment of the present disclosure discloses a text sequence generation method, device, equipment and medium. The method includes: obtaining an initial text sequence, and extracting initial text features from the initial text sequence; obtaining a structured text sequence, and extracting structured features from the structured text sequence; wherein, the structured text sequence and the The facts in the initial text sequence are associated; according to the initial text features and the structural features, a target text sequence is generated by fusion. The technical solution provided by the embodiments of the present disclosure generates a new text sequence by matching and merging different types of sequences associated with facts, thereby improving the accuracy and fluency of the target text.

Description

technical field [0001] Embodiments of the present disclosure relate to the field of artificial intelligence, and in particular, to a text sequence generation method, device, device, and medium. Background technique [0002] With the popularity of information application software, a large amount of information data needs to be processed and provided to users. Informational data can be presented in various forms, such as text, pictures, and videos. Text-based articles are an important form of information display. [0003] Due to the large number of articles to be processed, various automated text conversion technologies have been used to generate or convert articles so as to convert the original text materials into text articles that meet current needs. This technology is used for the conversion between different languages ​​or between different text forms, which is machine translation, and the conversion between articles and abstracts is automatic article summarization. ...

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): G06F40/205G06F40/103G06F40/126G06F16/35
CPCG06F40/205G06F40/103G06F40/126G06F16/355G06F40/44G06F40/284G06F40/216G06F40/143G06F40/30G06N3/0442G06N3/045G06N3/048G06F40/56G06F40/166
Inventor 李航乔超伊曾飒
Owner BEIJING BYTEDANCE NETWORK TECH CO LTD