PURE: a Prompt-based framework with dynamic Update mechanism for educational Relation Extraction

Abstract Traditional education systems obscure the diverse interconnections inherent within subject knowledge, thus failing to meet the current demand for personalized and adaptive learning experiences. Recent advances have explored various relation extraction techniques to construct educational kno...

Full description

Saved in:
Bibliographic Details
Main Authors: Xiaohui Cui, Yu Yang, Dongmei Li, Jinman Cui, Xiaolong Qu, Chao Song, Haoran Liu, Siyuan Ke
Format: Article
Language:English
Published: Springer 2024-12-01
Series:Complex & Intelligent Systems
Subjects:
Online Access:https://doi.org/10.1007/s40747-024-01692-w
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1832571141719326720
author Xiaohui Cui
Yu Yang
Dongmei Li
Jinman Cui
Xiaolong Qu
Chao Song
Haoran Liu
Siyuan Ke
author_facet Xiaohui Cui
Yu Yang
Dongmei Li
Jinman Cui
Xiaolong Qu
Chao Song
Haoran Liu
Siyuan Ke
author_sort Xiaohui Cui
collection DOAJ
description Abstract Traditional education systems obscure the diverse interconnections inherent within subject knowledge, thus failing to meet the current demand for personalized and adaptive learning experiences. Recent advances have explored various relation extraction techniques to construct educational knowledge graphs that integrate dispersed subject knowledge into a unified framework. However, educational conceptual entities are far more abstract and intricate compared to their real-world equivalents, and these techniques primarily focus on static knowledge, overlooking the dynamic nature of knowledge in practical learning and application scenarios. To address these issues, we propose a Prompt-based framework with dynamic Update mechanism for educational Relation Extraction (PURE). This framework embraces a prompt-tuning strategy and employs a more appropriate MacBERT-large model to encode the instances wrapped by prompt templates. Furthermore, we construct an instance-relation database that serves as an external knowledge base of our framework. A dynamic instance-relation update mechanism is proposed to refine the database, thus enhancing the accuracy of PURE in predicting new triples. We conduct experiments on a Data Structure course relation extraction dataset and three public datasets. The experimental results demonstrate that PURE achieves significant improvements and outperforms several state-of-the-art baselines in efficiency of extraction and utilization of educational information. Comparable performance is achieved even in more complex biomedical relation extraction, validating its robustness and applicability to other domains.
format Article
id doaj-art-0474f1454f9240e7b7aef32526943368
institution Kabale University
issn 2199-4536
2198-6053
language English
publishDate 2024-12-01
publisher Springer
record_format Article
series Complex & Intelligent Systems
spelling doaj-art-0474f1454f9240e7b7aef325269433682025-02-02T12:49:57ZengSpringerComplex & Intelligent Systems2199-45362198-60532024-12-0111111410.1007/s40747-024-01692-wPURE: a Prompt-based framework with dynamic Update mechanism for educational Relation ExtractionXiaohui Cui0Yu Yang1Dongmei Li2Jinman Cui3Xiaolong Qu4Chao Song5Haoran Liu6Siyuan Ke7School of Information Science and Technology, Beijing Forestry UniversitySchool of Information Science and Technology, Beijing Forestry UniversitySchool of Information Science and Technology, Beijing Forestry UniversitySchool of Information Science and Technology, Beijing Forestry UniversitySchool of Information Science and Technology, Beijing Forestry UniversitySchool of Information Science and Technology, Beijing Forestry UniversitySchool of Information Science and Technology, Beijing Forestry UniversitySchool of Information Science and Technology, Beijing Forestry UniversityAbstract Traditional education systems obscure the diverse interconnections inherent within subject knowledge, thus failing to meet the current demand for personalized and adaptive learning experiences. Recent advances have explored various relation extraction techniques to construct educational knowledge graphs that integrate dispersed subject knowledge into a unified framework. However, educational conceptual entities are far more abstract and intricate compared to their real-world equivalents, and these techniques primarily focus on static knowledge, overlooking the dynamic nature of knowledge in practical learning and application scenarios. To address these issues, we propose a Prompt-based framework with dynamic Update mechanism for educational Relation Extraction (PURE). This framework embraces a prompt-tuning strategy and employs a more appropriate MacBERT-large model to encode the instances wrapped by prompt templates. Furthermore, we construct an instance-relation database that serves as an external knowledge base of our framework. A dynamic instance-relation update mechanism is proposed to refine the database, thus enhancing the accuracy of PURE in predicting new triples. We conduct experiments on a Data Structure course relation extraction dataset and three public datasets. The experimental results demonstrate that PURE achieves significant improvements and outperforms several state-of-the-art baselines in efficiency of extraction and utilization of educational information. Comparable performance is achieved even in more complex biomedical relation extraction, validating its robustness and applicability to other domains.https://doi.org/10.1007/s40747-024-01692-wRelation extractionPrompt learningDynamic update mechanismEducationData Structure
spellingShingle Xiaohui Cui
Yu Yang
Dongmei Li
Jinman Cui
Xiaolong Qu
Chao Song
Haoran Liu
Siyuan Ke
PURE: a Prompt-based framework with dynamic Update mechanism for educational Relation Extraction
Complex & Intelligent Systems
Relation extraction
Prompt learning
Dynamic update mechanism
Education
Data Structure
title PURE: a Prompt-based framework with dynamic Update mechanism for educational Relation Extraction
title_full PURE: a Prompt-based framework with dynamic Update mechanism for educational Relation Extraction
title_fullStr PURE: a Prompt-based framework with dynamic Update mechanism for educational Relation Extraction
title_full_unstemmed PURE: a Prompt-based framework with dynamic Update mechanism for educational Relation Extraction
title_short PURE: a Prompt-based framework with dynamic Update mechanism for educational Relation Extraction
title_sort pure a prompt based framework with dynamic update mechanism for educational relation extraction
topic Relation extraction
Prompt learning
Dynamic update mechanism
Education
Data Structure
url https://doi.org/10.1007/s40747-024-01692-w
work_keys_str_mv AT xiaohuicui pureapromptbasedframeworkwithdynamicupdatemechanismforeducationalrelationextraction
AT yuyang pureapromptbasedframeworkwithdynamicupdatemechanismforeducationalrelationextraction
AT dongmeili pureapromptbasedframeworkwithdynamicupdatemechanismforeducationalrelationextraction
AT jinmancui pureapromptbasedframeworkwithdynamicupdatemechanismforeducationalrelationextraction
AT xiaolongqu pureapromptbasedframeworkwithdynamicupdatemechanismforeducationalrelationextraction
AT chaosong pureapromptbasedframeworkwithdynamicupdatemechanismforeducationalrelationextraction
AT haoranliu pureapromptbasedframeworkwithdynamicupdatemechanismforeducationalrelationextraction
AT siyuanke pureapromptbasedframeworkwithdynamicupdatemechanismforeducationalrelationextraction