A Study on a Food Pairing Knowledge Graph Construction Method Integrating Large Language Models and Relation Completion
DOI:
https://doi.org/10.63808/fewn.v2i3.430Keywords:
Food Pairing, Knowledge Graph, Large Language Model, Entity Normalization, Relation CompletionAbstract
Aiming at scattered knowledge sources, inconsistent entity expressions and insufficient relation extraction accuracy in food pairing, this paper proposes a food pairing knowledge graph construction method integrating large language models and relation completion. A domain ontology covering dishes, ingredients, nutrients, dietary restrictions, applicable populations and health goals is designed. Candidate entities and relations are then extracted from recipe texts, nutrition descriptions and dietary-restriction materials using a large language model, and entity normalization is performed through a domain dictionary and semantic embeddings. Finally, a relation scoring function integrating LLM confidence, semantic similarity and domain rules is used to filter, review and complete candidate triples. Experiments on a food pairing corpus show that the proposed method achieves a relation extraction F1 score of 88.71%, which is 6.05 percentage points higher than direct LLM extraction, and obtains a human-verified accuracy of 87.33% for completed relations. The results indicate that the proposed method can provide a reliable structured knowledge base for healthy diet recommendation and food pairing question answering.
References
[1] Zuo, M., Wang, F., Song, S., Yan, W., & Dai, X. (2024). “Intelligence+ food regulation”: Development process, application status, and future direction. Journal of Food Science and Technology, 42(3), 1–10. https://doi.org/10.12301/spxb202400331
[2] Misra, N. N., Dixit, Y., Al-Mallahi, A., Bhullar, M. S., Upadhyay, R., & Martynenko, A. (2022). IoT, big data, and artificial intelligence in agriculture and food industry. IEEE Internet of Things Journal, 9(9), 6305–6324. https://doi.org/10.1109/JIOT.2020.2998584
[3] Min, W. Q., Liu, C. L., Xu, L. Y., & Jiang, S. Q. (2022). Applications of knowledge graphs for food science and industry. Patterns, 3(5), Article 100484. https://doi.org/10.1016/j.patter.2022.100484
[4] Peng, C. Y., Xia, F., Naseriparsa, M., & Zhu, X. (2023). Knowledge graphs: Opportunities and challenges. Artificial Intelligence Review, 56(11), 13071–13102. https://doi.org/10.1007/s10462-023-10465-9
[5] Hogan, A., Blomqvist, E., Cochez, M., d’Amato, C., de Melo, G., Gutierrez, C., Kirrane, S., Labra Gayo, J. E., Navigli, R., Neumaier, S., Ngonga Ngomo, A.-C., Polleres, A., Roomp, K., Sack, H., Sequeda, J., & Simperl, E. (2021). Knowledge graphs. ACM Computing Surveys, 54(4), 1–37. https://doi.org/10.1145/3447772
[6] Auer, S., Bizer, C., Kobilarov, G., Lehmann, J., Cyganiak, R., & Ives, Z. (2007). DBpedia: A nucleus for a web of open data. In Proceedings of the 6th International Semantic Web Conference (ISWC) (pp. 722–735). Springer. https://doi.org/10.1007/978-3-642-04930-9_2
[7] Vaswani, A., Shazeer, N., Parmar, N., Uszkoreit, J., Jones, L., Gomez, A. N., Kaiser, Ł., & Polosukhin, I. (2017). Attention is all you need. In Advances in Neural Information Processing Systems (Vol. 30, pp. 5998–6008). https://doi.org/10.48550/arXiv.1706.03762
[8] Devlin, J., Chang, M. W., Lee, K., & Toutanova, K. (2019). BERT: Pre-training of deep bidirectional transformers for language understanding. In Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies (NAACL-HLT) (pp. 4171–4186). Association for Computational Linguistics. https://doi.org/10.18653/v1/N19-1423
[9] Brown, T. B., Mann, B., Ryder, N., Subbiah, M., Kaplan, J., Dhariwal, P., Neelakantan, A., Shyam, P., Sastry, G., Askell, A., Agarwal, S., Herbert-Voss, A., Krueger, G., Henighan, T., Child, R., Ramesh, A., Ziegler, D., Wu, J., Winter, C., … Amodei, D. (2020). Language models are few-shot learners. In Advances in Neural Information Processing Systems (Vol. 33, pp. 1877–1901). https://doi.org/10.5555/3495724.3495883
[10] Wei, J., Bosma, M., Zhao, V. Y., Guu, K., Yu, A. W., Lester, B., Du, N., Dai, A. M., & Le, Q. V. (2022). Finetuned language models are zero-shot learners. In Proceedings of the 10th International Conference on Learning Representations. https://doi.org/10.48550/arXiv.2109.01652
[11] Hu, E. J., Shen, Y., Wallis, P., Allen-Zhu, Z., Li, Y., Wang, S., Wang, L., & Chen, W. (2022). LoRA: Low-rank adaptation of large language models. In Proceedings of the 10th International Conference on Learning Representations. https://openreview.net/forum?id=nZeVKeeFYf9
[12] Dettmers, T., Pagnoni, A., Holtzman, A., & Zettlemoyer, L. (2023). QLoRA: Efficient finetuning of quantized large language models [Preprint]. arXiv. https://doi.org/10.48550/arXiv.2305.14314
[13] Vashishth, S., Sanyal, S., Nitin, V., & Talukdar, P. (2020). Composition-based multi-relational graph convolutional networks. In Proceedings of the 8th International Conference on Learning Representations. https://doi.org/10.48550/arXiv.1911.03082
[14] Gao, J., Luo, X., & Wang, H. (2022). Chinese causal event extraction using causality-associated graph neural network. Concurrency and Computation: Practice and Experience, 34(3), Article e6572. https://doi.org/10.1002/cpe.6572
[15] Li, Z., Sun, Y., Zhu, J., Tang, S., Zhang, C., & Ma, H. (2021). Improve relation extraction with dual attention-guided graph convolutional networks. Neural Computing and Applications, 33(6), 1773–1784. https://doi.org/10.1007/s00521-021-06410-2
[16] Pan, S., Luo, L., Wang, Y., Chen, C., Wang, J., & Wu, X. (2024). Unifying large language models and knowledge graphs: A roadmap. IEEE Transactions on Knowledge and Data Engineering, 36(7), 3580–3599. https://doi.org/10.1109/TKDE.2024.3352100
[17] Ibrahim, N., Aboulela, S., Ibrahim, A., & Kashef, R. (2024). A survey on augmenting knowledge graphs (KGs) with large language models (LLMs): Models, evaluation metrics, benchmarks, and challenges. Discover Artificial Intelligence, 4(1), 76. https://doi.org/10.1007/s44163-024-00137-0
[18] Ma, P., Tsai, S., He, Y., Jia, X., Zhen, D., Yu, N., Wang, Q., Ahuja, J. K. C., & Wei, C.-I. (2024). Large language models in food science: Innovations, applications, and future. Trends in Food Science & Technology, 148, Article 104488. https://doi.org/10.1016/j.tifs.2024.104488
[19] Bordes, A., Usunier, N., Garcia-Duran, A., Weston, J., & Yakhnenko, O. (2013). Translating embeddings for modeling multi-relational data. In Advances in Neural Information Processing Systems (Vol. 26, pp. 2787–2795). https://doi.org/10.5555/2999611.2999715
[20] Wei, Z., Su, J., Wang, Y., Tian, Y., & Chang, Y. (2020). A novel cascade binary tagging framework for relational triple extraction. In Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics (pp. 1476–1488). Association for Computational Linguistics. https://doi.org/10.18653/v1/2020.acl-main.136
[21] Yao, L., Mao, C., & Luo, Y. (2019). KG-BERT: BERT for knowledge graph completion [Preprint]. arXiv. https://doi.org/10.48550/arXiv.1909.03193
[22] Yang, Y. X. (2018). China food composition tables: Standard edition. Peking University Medical Press.
[23] Chinese Nutrition Society. (2022). Dietary guidelines for Chinese residents (2022). People’s Medical Publishing House.
Downloads
Published
Issue
Section
License
Copyright (c) 2026 Jia Yu, Tong Ji, Jiamin Zheng
This work is licensed under a Creative Commons Attribution 4.0 International License.