An essay automatic scoring method based on multi-stage learning

By combining shallow and deep features with a multi-stage learning approach, the accuracy problem of existing automatic essay scoring methods has been solved, achieving more comprehensive essay scoring, reducing the burden of manual scoring, and improving assessment accuracy.

CN115659954BActive Publication Date: 2026-06-26BEIJING UNIV OF TECH
View PDF 2 Cites 0 Cited by

Patent Information

Authority / Receiving Office
CN · China
Patent Type
Patents(China)
Current Assignee / Owner
BEIJING UNIV OF TECH
Filing Date
2022-10-31
Publication Date
2026-06-26

AI Technical Summary

Technical Problem

Existing automatic essay scoring methods struggle to comprehensively consider the essay's superficial linguistic features, deep semantic features, and human intervention, resulting in inaccurate scoring.

Method used

A multi-stage learning approach is adopted, combining shallow language features, sentiment features, topic relevance features, and writing style features. It expands topic words through knowledge graphs, integrates beautiful sentence recognition models and base learners to fuse deep semantic features, and uses ERNIE and bidirectional GRU to extract essay features for multi-dimensional scoring.

Benefits of technology

It improves the accuracy and consistency of essay scoring, reduces the burden of manual scoring, lowers assessment costs, and increases assessment precision.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN115659954B_ABST
    Figure CN115659954B_ABST
Patent Text Reader

Abstract

The application discloses a composition automatic scoring method based on multi-stage learning, and the method comprises the following steps: S1, extracting the shallow language features, emotional features and theme relevance features of the composition; S2, theme relevance feature extraction; S3, construction of a beautiful sentence identification model and extraction of composition style features; S4, training of a base learning machine; and S5, composition vector distributed representation and feature fusion model training and prediction. The application is applied to the field of automatic composition scoring, and a comprehensive and multi-dimensional composition scoring feature is designed for Chinese composition scoring, the detection and discovery of beautiful sentences in the composition are realized, and the beauty degree of language expression in the composition is better considered; meanwhile, the composition automatic scoring based on multi-stage learning is proposed, and multi-angle composition features are effectively combined for composition scoring.
Need to check novelty before this filing date? Find Prior Art