Scoring method of English composition integrating deep learning in higher vocational colleges

Author:

Feng Shuo,Yu Lixia,Liu Fen

Abstract

AbstractAlong with the progress of natural language processing technology and deep learning, the subjectivity, slow feedback, and long grading time of traditional English essay grading have been addressed. Intelligent English automatic scoring has been widely concerned by scholars. Given the limitations of topic relevance feature extraction methods and traditional automatic grading methods for English compositions, a topic decision model is proposed to calculate the topic relevance score of the topic richness in English composition. Then, based on the Score of Relevance Based on Topic Richness (TRSR) calculation method, an intelligent English composition scoring method combining artificial feature extraction and deep learning is designed. From the findings, the Topic Decision (TD) model achieved the best effect only when it was iterated 80 times. The corresponding accuracy, recall and F1 value were 0.97, 0.93 and 0.95 respectively. The model training loss finally stabilized at 0.03. The Intelligent English Composition Grading Method Integrating Deep Learning (DLIECG) method has the best overall performance and the best performance on dataset P. To sum up, the intelligent English composition scoring method has better effectiveness and reliability.

Publisher

Springer Science and Business Media LLC

Reference22 articles.

1. Urraca, C. N. & López, A. E. O. Productivity and graduality in the Layered Structure of the Word: Opaque word-formation in Old English. Spanish J. Appl. Linguist. 33(1), 202–226 (2020).

2. Liu, H. et al. Orientation cues-aware facial relationship representation for head pose estimation via transformer. IEEE Trans. Image Process. 32, 6289–6302 (2023).

3. Liu, H., Liu, T., Chen, Y., Zhang, Z. & Li, F. EHPE: Skeleton cues-based Gaussian coordinate encoding for efficient human pose estimation. IEEE Trans. Multimedia 2022, 859 (2022).

4. Liu, H. et al. EDMF: Efficient deep matrix factorization with review feature learning for industrial recommender system. IEEE Trans. Ind. Inf. 18(7), 4361–4371 (2021).

5. Liu, T., Wang, J., Yang, B. & Wang, X. NGDNet: Nonuniform Gaussian-label distribution learning for infrared head pose estimation and on-task behavior understanding in the classroom. Neurocomputing 436, 210–220 (2021).

同舟云学术

1.学者识别学者识别

2.学术分析学术分析

3.人才评估人才评估

"同舟云学术"是以全球学者为主线,采集、加工和组织学术论文而形成的新型学术文献查询和分析系统,可以对全球学者进行文献检索和人才价值评估。用户可以通过关注某些学科领域的顶尖人物而持续追踪该领域的学科进展和研究前沿。经过近期的数据扩容,当前同舟云学术共收录了国内外主流学术期刊6万余种,收集的期刊论文及会议论文总量共计约1.5亿篇,并以每天添加12000余篇中外论文的速度递增。我们也可以为用户提供个性化、定制化的学者数据。欢迎来电咨询!咨询电话:010-8811{复制后删除}0370

www.globalauthorid.com

TOP

Copyright © 2019-2024 北京同舟云网络信息技术有限公司
京公网安备11010802033243号  京ICP备18003416号-3