Automatic Scoring Method for Composition Based on Semantic Feature Fusion

doi:10.3969/j.issn.1006-2475.2024.06.002

Abstract

Abstract:
Abstract: Automatic composition scoring technology is a kind of natural language processing technology using machine learning. At present， end-to-end models based on deep learning have been widely used in the field of automatic essay scoring. However， because of the difficulty in obtaining correlations between different features in end-to-end models， Automatic Scoring Method for Composition Based on Semantic Feature Fusion （TSEF） has been proposed. This method is mainly divided into two stages: feature extraction and feature fusion. In the feature extraction stage， the Bert model is used to pre-train the input text， and a multi-head-attention mechanism is used to self-train the input text to supplement the shortcomings of pre-training; In the feature fusion stage， cross fusion methods are used to fuse the different features obtained in order to obtain a better performance model. In the experiment， TSEF was compared with many strong baselines， and the results demonstrated the effectiveness and robustness of our method.

Key words: Key words: automatic grading of essays, self-training, pre-training, cross fusion

CLC Number:

TP391

YUAN Hang, YANG Yong, REN Ge, Palidan Turson. Automatic Scoring Method for Composition Based on Semantic Feature Fusion[J]. Computer and Modernization, 2024, 0(06): 8-13.

References

［1］吴会芹. 用现代化手段辅助语言测试［J］. 外语电化教学， 2006（3）：49-53.
［2］ BURSTEIN J， KUKICH K， WOLFF S， et al. Automated scoring using a hybrid feature identification technique［C］// The 36th Annual Meeting of the Association for Computational Linguistics and the 17th International Conference on Computational Linguistics. ACL， 1998，1:206-210.
［3］崔建鹏. 自动作文评分的关键技术研究［D］. 成都：电子科技大学， 2020.
［4］ SUN J M， HE W T， WANG L F， et al. COVID-19: Epidemiology， evolution， and cross-disciplinary perspectives［J］. Trends in Molecular Medicine， 2020，26（5）:483-495.
［5］ VALENTI S， NERI F， CUCCHIARELLI A. An overview of current research on automated essay grading［J］. Journal of Information Technology Education: Research， 2003，2（1）:319-330.
［6］付瑞吉，王栋，王士进，等. 面向作文自动评分的优美句识别［J］. 中文信息学报， 2018，32（6）:88-97.
［7］ CHEN M， LI X. Relevance-based automated essay scoring via hierarchical recurrent model［C］// 2018 International Conference on Asian Language Processing （IALP）. IEEE， 2018:378-383.
［8］ ALIKANIOTIS D， YANNAKOUDAKIS H， REI M. Automatic text scoring using neural networks［C］// Proceedings of the 54th Annual Meeting of the Association for Computational Linguistics. ACL， 2016，1:715-725.
［9］ MAYFIELD E， ADAMSON D， WOODS B， et al. Beyond automated essay scoring: Forecasting and improving outcomes in middle and high school writing［C］// Companion Proceedings of the 8th International Conference on Learning Analytics and Knowledge. ACM， 2018:1-8.
［10］李琳，董璐璐，马洪超. 基于 BERT 的汉语作文自动评分研究［J］. 中国考试， 2022，5:73-80.
［11］ BROWN T， MANN B， RYDER N， et al. Language models are few-shot learners［J］. arXiv preprint arXiv：2005.14165，
2020.
［12］ KENTON J D M W C， TOUTANOVA L K. BERT: Pre-training of deep bidirectional transformers for language understanding［C］// Proceedings of NAACL-HLT. ACL， 2019:4171-4186.
［13］ YANG X， FENG S， ZHANG Y， et al. Multimodal sentiment detection based on multi-channel graph neural networks［C］// Proceedings of the 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Conference on Natural Language Processing. ACL， 2021，1:328-339.
［14］ YANG R， CAO J， WEN Z， et al. Enhancing automated essay scoring performance via fine-tuning pre-trained language models with combination of regression and ranking［C］// 2020 Findings of the Association for Computational Linguistics: EMNLP. ACL， 2020:1560-1569.
［15］刘明杨，秦兵，刘挺. 基于文采特征的高考作文自动评分［J］. 智能计算机与应用， 2016，6（1）：1-4.
［16］蔡黎，彭星源，赵军. 少数民族汉语考试的作文辅助评分系统研究［J］. 中文信息学报， 2011，25（5）:120-126.
［17］周明，贾艳明，周彩兰，等. 基于篇章结构的英文作文自动评分方法［J］. 计算机科学， 2019，46（3）:234-241.
［18］杨正祥，刘杰，袁克柔，等. 作文段落句间逻辑合理性等级评测［J］. 计算机应用与软件， 2019，36（9）:175-180.
［19］ DONG F， ZHANG Y， YANG J. Attention-based recurrent convolutional neural network for automatic essay scoring［C］// Proceedings of the 21st Conference on Computational Natural Language Learning. ACL， 2017:153-162.
［20］ TAY Y， PHAN M， TUAN L A， et al. Skipflow: Incorporating neural coherence features for end-to-end automatic text scoring［C］// Proceedings of the 2018 AAAI Conference on Artificial Intelligence. AAAI Press， 2018，32（1）.
［21］ LIU J， XU Y， ZHU Y. Automated essay scoring based on two-stage learning［J］. arXiv preprint arXiv:1901.07744， 2019.
［22］周险兵，樊小超，任鸽，等. 基于多层次语义特征的英文作文自动评分方法［J］. 计算机应用， 2021，41（8）:2205-2211.
［23］ RODRIGUEZ P U， JAFARIA， ORMEROD C M. Language models and automated essay scoring［J］. arXiv preprint arXiv：1909.09482，2019.
［24］ LI X， CHEN M， NIE J Y. SEDNN: Shared and enhanced deep neural network model for cross-prompt automated essay scoring［J］. Knowledge-Based Systems， 2020，210:106491.
［25］ ORMEROD C M， MALHOTRA A， JAFARI A. Automated essay scoring using efficient transformer-based language models［J］. arXiv preprint arXiv:2102.13136， 2021.
［26］陈建林. 大规模英语考试作文评分标准效度验证［J］. 中国考试， 2016（1）:29-38.
［27］ JIN C， HE B， HUI K， et al. TDNN: A two-stage deep neural network for prompt-independent automated essay scoring［C］// Proceedings of the 56th Annual Meeting of the Association for Computational Linguistics. ACL， 2018（1）:1088-1097.
［28］ TASHU T M， MAURYA C K， HORVATH T. Deep learning architecture for automatic essay scoring［J］. arXiv preprint arXiv:2206.08232， 2022.
［29］ ZHOU X， YANG L， FAN X， et al. Self-training vs pre-trained embeddings for automatic essay scoring［C］// Information Retrieval: The 27th China Conference. Springer， 2021:155-167.
［30］王菲. 大学英语作文自动评分系统（AES）的实证研究［J］. 科教文汇， 2014 （11）:99-100.
［31］梁茂成，文秋芳. 国外作文自动评分系统评述及启示［J］. 外语电化教学， 2007（5）:18-24.

[1]	WANG Hao-chang, LIU Ru-yi. Review of Relation Extraction Based on Pre-training Language Model [J]. Computer and Modernization, 2023, 0(01): 49-57.
[2]	HUANG Zhong-xiang, LI Ming. Text Classification Based on ALBERT Combined with Bidirectional Network [J]. Computer and Modernization, 2022, 0(10): 8-12.
[3]	ZHANG Zi-yun, WANG Wen-fa, MA Le-rong, DING Cang-feng. Research Progress of Text Summarization Model [J]. Computer and Modernization, 2022, 0(06): 56-66.
[4]	LU Yue, CAO Chun-ping. Microblog Rumor Detection Integrating User’s History and Dissemination Information [J]. Computer and Modernization, 2022, 0(06): 37-42.
[5]	LIU kun, ZENG Xi, QIU Zi-heng, CHEN Zhou-guo, . Text Clustering Algorithm Based on RoBERTa-WWM and HDBSCAN [J]. Computer and Modernization, 2022, 0(03): 48-52.
[6]	WANG Hao-chang, SUN Meng-ran, ZHAO Tie-jun. Low-resource Neural Machine Translation Based on ELMO [J]. Computer and Modernization, 2021, 0(07): 38-42.