[en] The growing demand for online education raises the question of which learning resources should be included in online programs to ensure students achieve their desired learning outcomes. By automatically identifying the core concepts in educational materials, teachers can select coherent and relevant resources for their courses. This work explores the use of Large Language Models (LLMs) to identify core concepts in educational resources. We propose three different pipelines for building knowledge graphs from lecture transcripts using LLMs and ontologies such as DBpedia. These knowledge graphs are then utilized to determine the central concepts (nodes) within the educational resources. Results show that LLM-constructed knowledge graphs when guided by ontologies, achieve state-of-the-art performance in core concept identification.
Disciplines :
Sciences informatiques
Auteur, co-auteur :
Reales, Daniel
Manrique, Rubén
GREVISSE, Christian ; University of Luxembourg > Faculty of Science, Technology and Medicine (FSTM) > Department of Life Sciences and Medicine (DLSM) > Medical Education
Co-auteurs externes :
yes
Langue du document :
Anglais
Titre :
Core Concept Identification in Educational Resources via Knowledge Graphs and Large Language Models
B. Abu-Salih S. Alotaibi A systematic literature review of knowledge graph construction and application in education Heliyon. 2024 10 3 e25383 10.1016/j.heliyon.2024.e25383
Q.U. Ain M.A. Chatti K.G.C. Bakar et al. Automatic construction of educational knowledge graphs: a word embedding-based approach Information. 2023 14 10 526 10.3390/info14100526
P. Chen Y. Lu V.W. Zheng et al. KnowEdu: a system to construct knowledge graph for education IEEE Access. 2018 6 31553 31563 10.1109/ACCESS.2018.2839607
de Paiva V, Gao Q, Kovalev P, et al. Extracting mathematical concepts with large language models. 2023. https://doi.org/10.48550/arXiv.2309.00642
Ding Z, Huang W, Liang J, et al. Improving recall of large language models: a model collaboration approach for relational triple extraction. 2024. https://doi.org/10.48550/arXiv.2404.09593
Li G, Wang P, Ke W. Revisiting large language models as zero-shot relation extractors. 2023. https://doi.org/10.48550/arXiv.2310.05028
Manrique R. LERECCI dataset. 2024. https://github.com/Ruframapi/LERECCI, Online. Accessed 01 July 2024
R. Manrique C. Grévisse O. Mariño et al. et al. R. Ichise F. Lecue T. Kawamura et al. et al. Knowledge graph-based core concept identification in learning resources Semantic Technology 2018 Cham Springer International Publishing 36 51 10.1007/978-3-030-04284-4_3
Manrique Piramanrique RF. Towards automatic learning resources organization via knowledge graphs, PhD thesis. Bogotá: Universidad de los Andes; 2019. http://hdl.handle.net/1992/41293
Papaluca A, Krefl D, Rodriguez SM, et al. Zero- and few-shots knowledge graph triplet extraction with large language models. 2023. https://doi.org/10.48550/arXiv.2312.01954,
Wadhwa S, Amir S, Wallace B. Revisiting Relation Extraction in the era of Large Language Models. In: Rogers A, Boyd-Graber J, Okazaki N, editors. Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers). Toronto: Association for Computational Linguistics; 2023. https://doi.org/10.18653/v1/2023.acl-long.868
Zhang K, Gutiérrez BJ, Su Y. Aligning instruction tasks unlocks large language models as zero-shot relation extractors. 2023. https://doi.org/10.48550/arXiv.2305.11159,
