Text generation method and device, electronic equipment and medium

A text and screening method technology, applied in the field of data processing, can solve problems such as poor generated results, and achieve the effect of improving poor generated results

Pending Publication Date: 2022-08-09
BEIJING YOUZHUJU NETWORK TECH CO LTD
View PDF0 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0005] Embodiments of the present disclosure provide a text generation method, device, electroni

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 device, electronic equipment and medium
  • Text generation method and device, electronic equipment and medium
  • Text generation method and device, electronic equipment and medium

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0035] figure 1 A schematic flowchart of a text generation method provided in the first embodiment of the present disclosure, the method can be applied to the situation of generating target text, the method can be executed by a text generation device, wherein the device can be implemented by software and / or hardware, and It is generally integrated on an electronic device. In this embodiment, the electronic device includes, but is not limited to, a computer, a notebook computer, a smart phone, or a tablet computer and other devices.

[0036] like figure 1 As shown, a text generation method provided by Embodiment 1 of the present disclosure includes the following steps:

[0037] S110. Obtain a text candidate set.

[0038] In this embodiment, the text candidate set can be understood as a set composed of multiple results (the results may include candidate texts) obtained by inputting the text to be processed into the corresponding text generation model. The text candidate set m...

Embodiment 2

[0073] figure 2 This is a schematic flowchart of a text generation method provided in Embodiment 2 of the present disclosure. The second embodiment is refined on the basis of the foregoing embodiments. In this embodiment, the process of acquiring the text candidate set and performing at least two screening method processing on the text candidate set to obtain the target text is described in detail. It should be noted that, for details that are not yet detailed in this embodiment, please refer to Embodiment 1.

[0074] like figure 2 As shown, a text generation method provided in Embodiment 2 of the present disclosure includes the following steps:

[0075] S210. Input the text to be processed into a processing model to obtain a text candidate set, and the processing model processes the text to be processed based on a sampling decoding method to obtain a text candidate set.

[0076] In this embodiment, the processing model can refer to a model that can be used to encode and...

Embodiment 3

[0120] Figure 4 This is a schematic structural diagram of a text generation apparatus provided in Embodiment 3 of the present disclosure, wherein the apparatus can be implemented by software and / or hardware, and is generally integrated on an electronic device.

[0121] like Figure 4 As shown, the apparatus includes: an acquisition module 310 and a processing module 320;

[0122] Wherein, the obtaining module 310 is configured to obtain a text candidate set, the text candidate set includes a plurality of candidate texts, and each of the candidate texts is a text obtained after processing the text to be processed;

[0123] The processing module 320 is configured to obtain the target text after performing at least two screening methods on the text candidate set with reference to the screening strategy of minimum Bayesian risk decoding;

[0124] Wherein, each of the screening methods is a screening method with different functions, the output of each screening is used as the in...

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 text generation method and device, electronic equipment and a medium. The method comprises the steps that a text candidate set is obtained, the text candidate set comprises a plurality of candidate texts, and each candidate text is a text obtained after a to-be-processed text is processed; performing at least two times of screening method processing on the text candidate set by referring to a screening strategy of minimum Bayesian risk decoding to obtain a target text; wherein the screening methods are screening methods with different functions, the output of each screening is used as the input of the next screening method, the result of each screening output is determined based on the evaluation score of the screened candidate text, and the evaluation score of the screened candidate text is determined based on the evaluation index of the used screening method. According to the method, the obtained text candidate set is processed through the screening method at least twice, and the problem that the result generated by a given text generation model is poor can be solved.

Description

technical field [0001] The embodiments of the present disclosure relate to the technical field of data processing, and in particular, to a text generation method, apparatus, electronic device, and medium. Background technique [0002] Text generation is an important part of Natural Language Processing (NLP), which aims to use machines to generate natural language text. [0003] Currently, a text generation model is usually given, and the text to be processed is input into the text generation model to generate corresponding text results. Among them, the text generation model refers to the system model for text generation, which can include an encoder and a decoder. The encoder encodes the input into a vector representation, and the decoder relies on the vector representation of the encoder. According to the specified decoding algorithm, word by word Generate the required text. [0004] However, using a given text generation model for text generation processing, the results ...

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): G06F40/253G06F40/51G06F16/33G06N3/04G06K9/62
CPCG06F40/253G06F40/51G06F16/3344G06F16/3346G06N3/047G06F18/217
Inventor 王涛赵程绮王明轩
Owner BEIJING YOUZHUJU NETWORK TECH 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