AI-Powered Multilingual Knowledge Systems: Enabling Cross-Lingual Access to Indigenous and Scientific Knowledge.
Keywords:
Multilingual Knowledge Systems, Cross-Lingual NLP, Neural Machine Translation, Semantic Knowledge Graph, Indigenous Knowledge Systems, Ontology, AI.Abstract
In the context of global knowledge proliferation, the linguistic heterogeneity of informational sources—particularly those emanating from Indigenous Knowledge Systems (IKS) and domain-specific scientific literature—significantly undermines equitable access and cross-cultural comprehension. Traditional Neural Machine Translation (NMT) and Natural Language Processing (NLP) pipelines inadequately preserve semantic nuance, cultural context, and conceptual fidelity, particularly for low-resource languages. This paper proposes a holistic AI-enabled multilingual knowledge system that integrates advanced transformer-based multilingual embeddings, semantic knowledge graphs, and ontology-driven inference mechanisms to facilitate semantic preservation, contextual alignment, and cross-lingual knowledge retrieval. Empirical evaluations demonstrate that the proposed framework enhances translation quality, semantic equivalence, and retrieval accuracy, thereby promoting inclusivity and democratized access to both indigenous and scientific knowledge.
References
Dewayanti, D. P. S., & Margana, M. (2022). Contextual understanding and neural machine translation accuracy: Evidence from cultural idioms. Englisia: Journal of Language, Education, and Humanities, 9(2), 145–159. https://doi.org/10.22373/ej.v9i2.24433
Han, Q. (2024). Research on the accuracy of machine translation in cross-cultural communication based on embedded neural networks. Journal of Intelligent & Fuzzy Systems, 46(2), 2567–2578. https://doi.org/10.3233/JIFS-235401
Indra Syahdewa, B., & Zulhendry, Z. (2024). Machine translation challenges and cultural sensitivity in multilingual communication. International Journal of Economics, Management and Accounting, 32(1), 45–61.
Katiyar, N., Verma, S., & Singh, A. (2024). Breaking language barriers: Advancements in machine translation for enhanced cross-lingual information retrieval. Journal of Electrical Systems, 20(4), 1123–1135.
Loboda, K. (2023). Machine translation and culture-bound texts: A translation studies perspective. Translation Studies, 16(3), 412–428. https://doi.org/10.1080/1750399X.2023.2238328
Naveen, P. (2024). Contextual and pragmatic challenges in neural machine translation systems. iScience, 27(6), 110214. https://doi.org/10.1016/j.isci.2024.110214
Sharoufi, H. A. (2025). Pragmatic and cultural challenges in machine translation. International Journal of Speech, Language and Communication, 9(1), 1–15.
Wang, R.-C., Hsieh, M.-C., & Lai, L.-C. (2026). From tacit knowledge distillation to AI-enabled culture revitalization. Social Sciences, 15(1), 18. https://doi.org/10.3390/socsci15010018
Yao, B., Jiang, M., Bobinac, T., Yang, D., & Hu, J. (2024). Benchmarking machine translation with cultural awareness. Findings of the Association for Computational Linguistics: EMNLP 2024, 8791–8806. https://doi.org/10.18653/v1/2024.findings-emnlp.765
Yao, J. (2025). Ethical and cultural considerations in machine translation systems. Journal of Information Systems Education and Management, 8(2), 55–68.
Downloads
How to Cite
Issue
Section
License
Copyright (c) 2026 International Journal of Engineering Science & Humanities
This work is licensed under a Creative Commons Attribution 4.0 International License.
