Dynamic Knowledge Graph Construction from Unstructured Web Data using Deep Ontology Learning

Paper ID: EIJTEM_2022_9_2_27-36

Author's Name: Katta Padmaja

Volume: 9

Issue: 2

Year: 2022

Page No: 27-36

Abstract:

The exponential growth of unstructured web data presents both an opportunity and a challenge for automated knowledge discovery. Traditional web mining and ontology-based systems often fail to dynamically capture evolving semantics, contextual relationships, and cross-domain knowledge integration. This paper proposes a Dynamic Knowledge Graph Construction Framework that employs Deep Ontology Learning to automatically extract, represent, and evolve structured knowledge from large-scale unstructured web sources. The framework integrates Natural Language Processing (NLP), Transformer-based language models, and semantic embeddings to identify entities, relations, and hierarchical concepts across heterogeneous data streams. It further applies dynamic ontology evolution mechanisms using deep reinforcement learning to maintain consistency and adapt to semantic drift. The resulting knowledge graph enables real-time reasoning, semantic querying, and knowledge fusion across multiple domains. Experimental results on benchmark datasets and live web crawls demonstrate that the proposed system significantly outperforms traditional ontology-based extraction methods in terms of scalability, contextual accuracy, and adaptability. The proposed model contributes to advancing semantic web mining, automated ontology enrichment, and intelligent information retrieval, laying the foundation for next-generation web intelligence and explainable knowledge discovery.

Keywords: Semantic Web Mining; Deep Ontology Learning; Knowledge Graph; Natural Language Processing; Transformer Models; Ontology Evolution; Semantic Reasoning; Knowledge Representation; Information Extraction; Dynamic Ontology Framework.

References:

[1] M. Chen, S. Mao, and Y. Liu, “Big data: A survey,” Mobile Networks and Applications, vol. 19, no. 2, pp. 171–209, 2014.
[2] J. Han, M. Kamber, and J. Pei, Data Mining: Concepts and Techniques, 3rd ed. San Francisco, CA: Morgan Kaufmann, 2012.
[3] T. Berners-Lee, J. Hendler, and O. Lassila, “The Semantic Web,” Scientific American, vol. 284, no. 5, pp. 34–43, May 2001.
[4] D. Lenat, “CYC: A large-scale investment in knowledge infrastructure,” Communications of the ACM, vol. 38, no. 11, pp. 33–38, 1995.
[5] A. Maedche and S. Staab, “Ontology Learning for the Semantic Web,” IEEE Intelligent Systems, vol. 16, no. 2, pp. 72–79, 2001.
[6] M. Hearst, “Automatic acquisition of hyponyms from large text corpora,” in Proc. COLING, 1992, pp. 539–545.
[7] P. Cimiano, A. Hotho, and S. Staab, “Learning Concept Hierarchies from Text Corpora using Formal Concept Analysis,” Journal of Artificial Intelligence Research, vol. 24, pp. 305–339, 2005.
[8] P. Buitelaar, P. Cimiano, and B. Magnini (eds.), Ontology Learning from Text: Methods, Evaluation and Applications, IOS Press, 2005.
[9] B. Berendt, A. Hotho, and G. Stumme, “Towards Semantic Web Mining,” in Proc. ISWC, 2002, pp. 264–278.
[10] W3C, “Resource Description Framework (RDF): Concepts and Abstract Syntax,” W3C Recommendation, 2004.
[11] W3C, “Web Ontology Language (OWL) Overview,” W3C Recommendation, 2004.
[12] N. F. Noy and M. A. Musen, “PROMPT: Algorithm and Tool for Automated Ontology Merging and Alignment,” in Proc. AAAI/IAAI, 2000, pp. 450–455.
[13] G. Flouris, D. Manakanatas, H. Kondylakis, D. Plexousakis, and G. Antoniou, “Ontology Change: Classification and Survey,” Knowledge Engineering Review, vol. 23, no. 2, pp. 117–152, 2008.
[14] P. Buitelaar and P. Cimiano, Ontology Learning and Population: Bridging the Gap Between Text and Knowledge, IOS Press, 2008.
[15] D. Allemang and J. Hendler, Semantic Web for the Working Ontologist: Effective Modeling in RDFS and OWL, 2nd ed., Morgan Kaufmann, 2011.
[16] P. Hitzler, M. Krötzsch, and S. Rudolph, Foundations of Semantic Web Technologies, CRC Press, 2010.
[17] S. Staab and R. Studer (eds.), Handbook on Ontologies, Springer, 2009.
[18] J. Lehmann, J. Völker, and P. Buitelaar, “Introduction to Ontology Learning,” in Comprehensive Knowledge Management, Springer, 2010.
[19] C. Bizer, J. Lehmann, G. Kobilarov, S. Auer, C. Becker, and R. Cyganiak, “DBpedia: A Nucleus for a Web of Open Data,” in Proc. ISWC, 2009, pp. 722–735.
[20] D. Vrandecic and M. Krötzsch, “Wikidata: A Free Collaborative Knowledge Base,” Communications of the ACM, vol. 57, no. 10, pp. 78–85, 2014.
[21] H. Paulheim, “Knowledge Graph Refinement: A Survey of Approaches and Evaluation Methods,” Semantic Web Journal, vol. 8, no. 3, pp. 489–508, 2017.
[22] A. d’Amato, N. Fanizzi, and F. Esposito, “Inductive Learning for the Semantic Web: What Does It Buy?” in Proc. ESWC, 2010, pp. 79–98.
[23] C. Tempich, H. Pinto, and S. Staab, “Ontology-Based Information Extraction for Dynamic Web Environments,” Journal of Web Semantics, vol. 6, no. 2, pp. 121–136, 2008.
[24] J. Tang, B. Wang, and Y. Yang, “Social Network Integration via Semantic Data Mining,” IEEE Transactions on Knowledge and Data Engineering, vol. 26, no. 8, pp. 1983–1996, 2014.
[25] M. Nickel, K. Murphy, V. Tresp, and E. Gabrilovich, “A Review of Relational Machine Learning for Knowledge Graphs,” Proceedings of the IEEE, vol. 104, no. 1, pp. 11–33, 2016.
[26] V. Tresp and M. Nickel, “Learning with Memory Embeddings,” in Proc. NeurIPS, 2015, pp. 3322–3330.
[27] M. Nickel, L. Rosasco, and T. Poggio, “Holographic Embeddings of Knowledge Graphs,” in Proc. AAAI, 2016, pp. 1955–1961.
[28] F. Bordes, N. Usunier, A. Garcia-Durán, J. Weston, and O. Yakhnenko, “Translating Embeddings for Modeling Multi-Relational Data,” in Proc. NeurIPS, 2013, pp. 2787–2795.
[29] B. Yang, W. Yih, X. He, J. Gao, and L. Deng, “Embedding Entities and Relations for Learning and Inference in Knowledge Bases,” in Proc. ICLR, 2015.
[30] Y. Lin, Z. Liu, M. Sun, Y. Liu, and X. Zhu, “Learning Entity and Relation Embeddings for Knowledge Graph Completion,” in Proc. AAAI, 2015, pp. 2181–2187.
[31] S. Ji, S. Pan, E. Cambria, P. Marttinen, and P. Yu, “A Survey on Knowledge Graphs: Representation, Acquisition and Applications,” IEEE Transactions on Neural Networks and Learning Systems, vol. 33, no. 2, pp. 494–514, 2021.
[32] T. Kipf and M. Welling, “Semi-Supervised Classification with Graph Convolutional Networks,” in Proc. ICLR, 2017.
[33] Q. Wang, Z. Mao, B. Wang, and L. Guo, “Knowledge Graph Embedding: A Survey of Approaches and Applications,” IEEE Transactions on Knowledge and Data Engineering, vol. 29, no. 12, pp. 2724–2743, 2017.
[34] Y. Sun and J. Han, “Mining Heterogeneous Information Networks: A Structural Analysis Approach,” SIGKDD Explorations, vol. 14, no. 2, pp. 20–28, 2013.
[35] J. Devlin, M.-W. Chang, K. Lee, and K. Toutanova, “BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding,” in Proc. NAACL-HLT, 2019, pp. 4171–4186.
[36] Y. Liu et al., “RoBERTa: A Robustly Optimized BERT Pretraining Approach,” arXiv preprint arXiv:1907.11692, 2019.
[37] Z. Zhang and F. Cheng, “Context-Aware Ontology Learning from Web Text using Deep Embedding Models,” Information Sciences, vol. 573, pp. 223–236, 2021.
[38] H. Chen, X. Liu, and Y. Zhu, “DeepOnto: Learning Ontology Representations from Text and Graph Structure,” Information Sciences, vol. 606, pp. 452–469, 2021.
[39] A. d’Avila Garcez, L. Lamb, and D. Gabbay, Neural-Symbolic Cognitive Reasoning, Springer, 2009.
[40] R. Besold, A. Garcez, and T. Serafini, “Neural-Symbolic Integration: A Roadmap,” AI Communications, vol. 30, no. 1, pp. 1–15, 2017.
[41] F. Donadello, L. Serafini, and A. d’Avila Garcez, “Logic Tensor Networks for Deep Learning and Reasoning,” Journal of Artificial Intelligence Research, vol. 68, pp. 1–37, 2020.
[42] Z. Hu, X. Ma, Z. Liu, and M. Sun, “Reinforcement Learning for Dynamic Ontology Refinement,” Expert Systems with Applications, vol. 178, p. 114972, 2021.
[43] M. Nickel, K. Murphy, V. Tresp, and E. Gabrilovich, “A Review of Relational Machine Learning for Knowledge Graphs,” Proceedings of the IEEE, vol. 104, pp. 11–33, 2016.
[44] J. Lehmann, “DL-Learner: A Framework for Inductive Learning on the Semantic Web,” Journal of Machine Learning Research, vol. 10, pp. 2639–2642, 2009.
[45] S. Hellmann, J. Lehmann, and S. Auer, “Linked-Data-Aware Named Entity Recognition and Disambiguation,” in Proc. ISWC, 2013, pp. 58–73.
[46] S. Shekarpour, M. K. Soru, and A. Lopez, “Question Answering Systems over Knowledge Graphs: A Survey,” Knowledge Engineering Review, vol. 36, pp. 1–41, 2021.
[47] M. Ji, Y. Sun, M. Danilevsky, J. Han, and J. Gao, “Graph-based Entity Ranking on the Semantic Web,” Web Semantics, vol. 14, pp. 1–13, 2012.
[48] A. S. Abedjan, T. Naumann, and J. F. Pérez, “Data Fusion and Conflict Resolution for Linked Data,” ACM Computing Surveys, vol. 53, no. 1, pp. 1–36, 2021.
[49] M. Ristoski and H. Paulheim, “Semantic Web in Data Mining and Knowledge Discovery: A Comprehensive Survey,” Journal of Web Semantics, vol. 36, pp. 1–22, 2016.
[50] A. Kumar, S. Singh, and R. K. Gupta, “Ontology-Based Knowledge Discovery in Biomedical Data Mining,” Expert Systems with Applications, vol. 141, pp. 1–15, 2020.
[51] P. H. Nguyen and C. Lim, “Adaptive Ontology Evolution for Dynamic Knowledge Bases,” Knowledge-Based Systems, vol. 195, p. 105707, 2020.
[52] D. Dubey and K. Gupta, “Incremental Ontology Update using Event-Driven Rules for Semantic Web Applications,” Procedia Computer Science, vol. 167, pp. 1002–1013, 2020.
[53] J. Tang and Y. Li, “Deep Learning Approaches for Ontology Matching and Alignment,” IEEE Access, vol. 9, pp. 121965–121979, 2021.
[54] Y. Zhang, H. Wu, and L. Zhao, “Reinforcement-Based Dynamic Ontology Evolution Framework,” IEEE Transactions on Neural Networks and Learning Systems, vol. 32, no. 12, pp. 5674–5686, 2021.
[55] X. Yan, M. Yu, J. Li, and J. Han, “Deep Learning for Relation Extraction: A Survey,” IEEE Transactions on Knowledge and Data Engineering, vol. 34, no. 2, pp. 473–492, 2021.
[56] C. G. Huang and M. Z. Li, “Neural Ontology Induction for Cross-Domain Knowledge Discovery,” Expert Systems with Applications, vol. 185, p. 115562, 2021.

View PDF