Hybrid Neural-Symbolic Natural Language Understanding with Deterministic Routing for Multi-Intent Command Processing
DOI:
https://doi.org/10.15662/IJEETR.2026.0802233Keywords:
Hybrid Natural Language Understanding, Neural–Symbolic AI, Multi-Intent Detection, Deterministic Routing, Slot Filling, Knowledge Graph Validation, Command UnderstandingAbstract
Natural language understanding (NLU) systems used in command-driven interfaces must process both simple and multi-intent queries while maintaining high accuracy and low latency. Conventional approaches typically rely on a single model architecture, which can lead to inefficiencies when queries vary significantly in complexity. To address this limitation, this paper proposes a hybrid neural–symbolic NLU framework that integrates deterministic routing, machine learning (ML), deep learning (DL), slot extraction, and knowledge graph validation
The proposed system employs a deterministic complexity-aware routing mechanism that directs low-complexity queries to a lightweight ML ensemble classifier, while complex or multi-intent queries are processed by a transformer-based DL model for deeper semantic analysis. The predicted intents are then passed to a sequence-to-structure slot extraction module based on the T5 architecture to identify structured parameters required for command execution. A symbolic knowledge graph layer further performs intent compatibility checks, dependency validation, and slot constraint verification to ensure logical consistency in the final interpretation
Experimental evaluation demonstrates that the proposed hybrid architecture outperforms ML-only and DL-only baselines. The system achieves 98.0% intent accuracy and 95.9% slot accuracy while maintaining an average end-to-end latency of 333.4 ms through efficient routing. These results indicate that integrating neural learning with symbolic validation and deterministic routing provides an effective and scalable solution for multi-intent command understanding in offline intelligent agents
References
1. A. S. M. Zailan, N. H. I. Teo, N. A. S. Abdullah, and M. Joy, “State of the Art in Intent Detection and Slot Filling for Question Answering System: A Systematic Literature Review,” International Journal of Advanced Computer Science and Applications, vol. 14, no. 11, pp. 15–27, 2023.
2. D. Wu, R. Fang, L. Jiang, S. Song, X. Huang, S. Wang, Z. Li, L. Shi, M. Bao, Y. Li, and H. Huang, “Multi-Intent Spoken Language Understanding: A Survey of Methods, Trends, and Challenges,” Vicinagearth, vol. 2, 2025.
3. C. Zhang, Y. Li, N. Du, W. Fan, and P. S. Yu, “Joint Slot Filling and Intent Detection via Capsule Neural Networks,” Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics (ACL), 2019.
4. Y. I. Muhammad, N. Salim, and A. Zainal, “Joint Intent Detection and Slot Filling with Syntactic and Semantic Features Using Multichannel CNN-BiLSTM,” PeerJ Computer Science, 2024.
5. L. Qin, X. Xu, W. Che, and T. Liu, “AGIF: An Adaptive Graph-Interactive Framework for Joint Multiple Intent Detection and Slot Filling,” Findings of the Association for Computational Linguistics: EMNLP, 2020.
6. Z. Ding, Z. Yang, H. Lin, and J. Wang, “Focus on Interaction: A Novel Dynamic Graph Model for Joint Multiple Intent Detection and Slot Filling,” Proceedings of the International Joint Conference on Artificial Intelligence (IJCAI), 2021.
7. T. Pham, C. Tran, and D. Q. Nguyen, “MISCA: A Joint Model for Multiple Intent Detection and Slot Filling with Intent–Slot Co-Attention,” Findings of the Association for Computational Linguistics: EMNLP, 2023.
8. B. Xing and I. W. Tsang, “Co-Guiding Net: Achieving Mutual Guidances between Multiple Intent Detection and Slot Filling via Heterogeneous Semantics-Label Graphs,” Proceedings of the Conference on Empirical Methods in Natural Language Processing (EMNLP), 2022.
9. Y. Chen and Z. Luo, “Pre-Trained Joint Model for Intent Classification and Slot Filling with Semantic Feature Fusion,” Sensors, vol. 23, no. 5, 2023.
10. [10] M. Hardalov, I. Koychev, and P. Nakov, “Enriched Pre-Trained Transformers for Joint Slot Filling and Intent Detection,” Proceedings of the International Conference on Recent Advances in Natural Language Processing (RANLP), 2023.
11. [11] R. Gangadharaiah and B. Narayanaswamy, “Joint Multiple Intent Detection and Slot Labeling for Goal-Oriented Dialogue,” Proceedings of the North American Chapter of the Association for Computational Linguistics (NAACL-HLT), 2019.
12. C.Nagarajan and M.Madheswaran - ‘Stability Analysis of Series Parallel Resonant Converter with Fuzzy Logic Controller Using State Space Techniques’- Taylor &Francis, Electric Power Components and Systems, Vol.39 (8), pp.780-793, May 2011. DOI: 10.1080/15325008.2010.541746
13. C.Nagarajan and M.Madheswaran - ‘Experimental verification and stability state space analysis of CLL-T Series Parallel Resonant Converter’ - Journal of Electrical Engineering, Vol.63 (6), pp.365-372, Dec.2012. DOI: 10.2478/v10187-012-0054-2
14. C.Nagarajan and M.Madheswaran - ‘Performance Analysis of LCL-T Resonant Converter with Fuzzy/PID Using State Space Analysis’- Springer, Electrical Engineering, Vol.93 (3), pp.167-178, September 2011. DOI 10.1007/s00202-011-0203-9
15. S.Tamilselvi, R.Prakash, C.Nagarajan,“Solar System Integrated Smart Grid Utilizing Hybrid Coot-Genetic Algorithm Optimized ANN Controller” Iranian Journal Of Science And Technology-Transactions Of Electrical Engineering, DOI10.1007/s40998-025-00917-z,2025
16. S.Tamilselvi, R.Prakash, C.Nagarajan,“ Adaptive sliding mode control of multilevel grid-connected inverters using reinforcement learning for enhanced LVRT performance” Electric Power Systems Research 253 (2026) 112428, doi.org/10.1016/j.epsr.2025.112428
17. S.Thirunavukkarasu, C. Nagarajan, 2024, “Performance Investigation on OCF and SCF study in BLDC machine using FTANN Controller," Journal of Electrical Engineering And Technology, Volume 20, pages 2675–2688, (2025), doi.org/10.1007/s42835-024-02126-w
18. C. Nagarajan, M.Madheswaran and D.Ramasubramanian- ‘Development of DSP based Robust Control Method for General Resonant Converter Topologies using Transfer Function Model’- Acta Electrotechnica et Informatica Journal , Vol.13 (2), pp.18-31,April-June.2013, DOI: 10.2478/aeei-2013-0025.
19. C.Nagarajan and M.Madheswaran - ‘DSP Based Fuzzy Controller for Series Parallel Resonant converter’- Springer, Frontiers of Electrical and Electronic Engineering, Vol. 7(4), pp. 438-446, Dec.12. DOI 10.1007/s11460-012-0212-0.
20. C.Nagarajan and M.Madheswaran - ‘Experimental Study and steady state stability analysis of CLL-T Series Parallel Resonant Converter with Fuzzy controller using State Space Analysis’- Iranian Journal of Electrical & Electronic Engineering, Vol.8 (3), pp.259-267, September 2012.
21. C.Nagarajan and M.Madheswaran, “Analysis and Simulation of LCL Series Resonant Full Bridge Converter Using PWM Technique with Load Independent Operation” has been presented in ICTES’08, a IEEE / IET International Conference organized by M.G.R.University, Chennai.Vol.no.1, pp.190-195, Dec.2007
22. Suganthi Mullainathan, Ramesh Natarajan, “An SPSS and CNN modelling based quality assessment using ceramic materials and membrane filtration techniques”, Revista Materia (Rio J.) Vol. 30, 2025, DOI: https://doi.org/10.1590/1517-7076-RMAT-2024-0721
23. M Suganthi, N Ramesh, “Treatment of water using natural zeolite as membrane filter”, Journal of Environmental Protection and Ecology, Volume 23, Issue 2, pp: 520-530,2022
24. T. He, X. Xu, Y. Wu, H. Wang, and J. Chen, “Multitask Learning with Knowledge Base for Joint Intent Detection and Slot Filling,” Applied Sciences, vol. 11, 2021.
25. L. Qin, F. Wei, T. Xie, X. Xu, W. Che, and T. Liu, “GL-GIN: Fast and Accurate Non-Autoregressive Model for Joint Multiple Intent Detection and Slot Filling,” Proceedings of the 59th Annual Meeting of the Association for Computational Linguistics (ACL), 2021.
26. S. Zhang, Z. You, X. Qi, P. Liu, G. Wu, K. Xia, and S. Huang, “LCAN: A Label-Aware Contrastive Attention Network for Multi-Intent Recognition and Slot Filling in Task-Oriented Dialogue Systems,” Findings of the Association for Computational Linguistics: EMNLP, 2025.
27. Y. Song, J. Zhao, I. G. Harris, S. B. Koehler, and A. Abdullah, “PCMID: Multi-Intent Detection through Supervised Prototypical Contrastive Learning,” Proceedings of the Conference on Empirical Methods in Natural Language Processing (EMNLP), 2022.
28. I. Vulić, I. Casanueva, G. Spithourakis, A. Mondal, T. Wen, and P. Budzianowski, “Multi-Label Intent Detection via Contrastive Task Specialization of Sentence Encoders,” Proceedings of the Conference on Empirical Methods in Natural Language Processing (EMNLP), 2022.
29. Mathew, A., & Alex, H. (2025). Federated Learning for Secure Genomic Research: Privacy-Preserving AI Solutions for Precision Medicine. Science and Technology: Developments and Applications Vol. 9, 36-43.
30. Jagadeesh, S., & Soundappan, R. S. (2014). Survey on knowledge discovery in speech emotion detection. International Journal of Innovative Research in Computer and Communication Engineering, 2(5), 4476–4481. Retrieved from https://ijircce.com/admin/main/storage/app/pdf/i7mLTWLAd6a4VqXoYxeMRM6m0zylGcBFKaMTHo5H.pdf
31. Soundappan, S. J. (2022). AI-Based Fault Detection and Isolation for Reliability in Modern Power Systems. International Journal of Research Publications in Engineering, Technology and Management (IJRPETM), 5(4), 7106-7110.
