An automatic composition score calculation method based on sentence fluency

A computing method and smooth technology, applied in computing, neural learning methods, semantic tool creation, etc., to achieve the effect of improving the robustness of the model

Active Publication Date: 2022-07-05
UNIV OF ELECTRONICS SCI & TECH OF CHINA
View PDF11 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

However, identifying and defining these characteristics is always an empirical process that requires extensive experience and domain expertise

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
  • An automatic composition score calculation method based on sentence fluency
  • An automatic composition score calculation method based on sentence fluency
  • An automatic composition score calculation method based on sentence fluency

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0061] In order to have a clearer understanding of the technical features, objects and effects of the present invention, the specific embodiments of the present invention will now be described with reference to the accompanying drawings.

[0062] like figure 1 As shown, an automatic composition score calculation method based on sentence fluency, including sentence vector distributed representation, sentence feature extraction, inter-sentence relationship feature extraction, and multi-layer perceptron (MLP) model training prediction;

[0063] The sentence vector distributed representation is used to form a sentence representation matrix through different word vector distributed representation methods;

[0064] The sentence feature extraction is used to extract sentence features through a convolution layer and a pooling layer;

[0065] The inter-sentence relationship feature extraction is used to extract inter-sentence relationship features through the Self-attention model;

...

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 an automatic composition scoring calculation method based on sentence fluency. The method includes S1: sentence vector distributed representation; S2: sentence feature extraction; S3: relationship feature extraction between sentences; S4: multi-layer perceptron model training predict. The invention proposes to apply the sentence fluency index to the field of automatic composition scoring, which is used to realize the function of detecting and discovering semantically incoherent sentences in the composition, and has a lower score for the semantically irrelevant words and sick sentences in the composition.

Description

technical field [0001] The invention belongs to the technical field of natural language understanding, and in particular relates to an automatic composition scoring calculation method based on sentence fluency. Background technique [0002] Structural modeling of coherent text is an important problem in natural language processing. Coherence is a key property of any well-organized text. It assesses the degree of logical coherence of the text, helping to record a set of sentences in a logically consistent order, which is at the heart of many text synthesis tasks such as text generation and multi-document summarization. A good article has a special high-level logic and topic structure, and the actual word and sentence choices and transitions between them are for conveying the purpose of the text. Since the concept of coherence is too abstract to capture and measure, it is difficult to explicitly describe the properties of textual coherence, and sentence coherence computationa...

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): G06F16/36G06F40/289G06N3/04G06N3/08
CPCG06F16/367G06F40/289G06N3/08G06N3/048G06N3/045
Inventor 郝玉洁徐佳俊党元桑玉坤李继演伍双楠
Owner UNIV OF ELECTRONICS SCI & TECH OF CHINA
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