Text scoring method, device and system

A text and syntax technology, applied in the field of deep learning, can solve the problems of single features and low reliability of scoring results, and achieve the effect of enhancing reliability

Pending Publication Date: 2020-05-05
HUAZHONG NORMAL UNIV
View PDF14 Cites 10 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0002] In related technologies, the traditional text scoring method is mainly to extract the shallow text features of the text or extract the semantic information of the text, and use simple regression, classification, and sorting methods to train the extracted features; because the features extracted in this scoring method Relatively single, resulting in low reliability of scoring results

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 scoring method, device and system
  • Text scoring method, device and system
  • Text scoring method, device and system

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0038] see figure 1 A flow chart of a text scoring method shown, the method includes the following steps:

[0039] Step S102, acquiring the text to be scored.

[0040] The text to be scored refers to the text whose content needs to be scored, and the text can be an English composition, an English article, etc., or a text in other languages. Scoring refers to making a judgment on the grammar, syntax, semantics, and topic relevance of the text. Generally speaking, the higher the score, the more the grammar of the text to be scored has no errors, the syntax is rich, the semantics is correct, and The text content is highly relevant to the topic.

[0041] Step S104, extracting the text features of the text; the text features include shallow language features, syntactic features, semantic features and theme features; wherein, the above semantic features are used to represent the semantic coherence in the text; the above theme features are used to represent the text and Relevance ...

Embodiment 2

[0048] The embodiment of the present invention also provides another text scoring method; this method is implemented on the basis of the method in the above embodiment; this method focuses on the specific implementation of extracting the text features of the text.

[0049] Such as figure 2 A flow chart of another text scoring method shown, the method includes the following steps:

[0050] Step S202, acquiring the text to be scored.

[0051] Step S204, extract shallow language features, syntactic features, semantic features and topic features from the text through the preset transformer encoder.

[0052] Through the analysis of the writing requirements of the new domestic junior high school English curriculum standards and the English composition scoring standards, we can see that the junior high school English composition scoring mainly considers the two aspects of content and language, and considers the content aspects (content points, semantic coherence, etc.) The importa...

Embodiment 3

[0101] Corresponding to the above method embodiment, the embodiment of the present invention provides a text scoring device, such as Image 6 A structural schematic diagram of a text scoring device shown, the device comprising:

[0102] Text obtaining module 61, for obtaining the text to be scored;

[0103] The feature extraction module 62 is used to extract the text features of the text; the text features include shallow language features, syntactic features, semantic features and theme features; wherein, the semantic features are used to represent the semantic coherence in the text; the theme features are used to represent the text Relevance to preset text topics;

[0104] The result output module 63 is used for inputting the text features into the pre-set scoring model to obtain the output result;

[0105] A score determining module 64, configured to determine the score of the text according to the output result.

[0106] A text scoring device provided by an embodiment o...

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 scoring method, device and system. The method comprises the steps of obtaining a to-be-scored text; extracting text features of the text; wherein the text features comprise shallow language features, syntax features, semantic features and topic features; wherein the semantic features are used for representing semantic coherence in the text; wherein the topic featuresare used for representing the relevancy between the text and a preset text topic; inputting the text features into a preset scoring model to obtain an output result; and determining the score of the text according to the output result. Shallow language features, syntax features, semantic features and theme features are extracted from a text to be scored to serve as text features, the text featuresare input into a preset scoring model, and an output result output by the scoring model serves as a score of the text. Comprehensive evaluation and analysis are carried out on four aspects of shallowlanguage features, syntax features, semantic features and theme features, so that the reliability of a scoring result can be enhanced.

Description

technical field [0001] The present invention relates to the technical field of deep learning, in particular to a text scoring method, device and system. Background technique [0002] In related technologies, the traditional text scoring method is mainly to extract the shallow text features of the text or extract the semantic information of the text, and use simple regression, classification, and sorting methods to train the extracted features; because the features extracted in this scoring method Relatively single, resulting in low reliability of the scoring results. Contents of the invention [0003] In view of this, the object of the present invention is to provide a text scoring method, device and system to enhance the reliability of scoring results. [0004] In the first aspect, the embodiment of the present invention provides a text scoring method, including: obtaining the text to be scored; extracting the text features of the text; the text features include shallow ...

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): G06F40/205G06F40/211G06F40/30G06F16/33
CPCG06F16/3344
Inventor 黄涛张浩刘三女牙杨宗凯杨华利刘子迁
Owner HUAZHONG NORMAL UNIV
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

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

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap