Textual data from sources such as social media, messaging, and OCR often contain problematic elements – they are noisy, ambiguous, or incomplete – posing challenges for traditional natural language processing (NLP) techniques. This paper presents a hybrid neuro-fuzzy modeling approach to robustly process such problematic text data. We combine fuzzy logic’s strength in handling uncertainty and imprecision with neural networks’ learning capability to create a software system that can normalize noisy text, interpret ambiguous language, and make reliable decisions even with incomplete information. We outline the architecture of the proposed system, which integrates fuzzy inference modules (capturing expert linguistic rules and similarity measures) with trainable neural network components that adapt these rules to data. Practical examples demonstrate how the system corrects slang and spelling variations and resolves ambiguities in context.

neuro-fuzzy modeling, fuzzy logic, noisy text processing, text normalization, natural language processing (nlp), text classification, interpretability.

Bagla, K., Natarajan, T., & Swaminathan, M. (2021). Impact of textual noise on NLP models. Proceedings of the AAAI Conference on Artificial Intelligence, 35(17), 14951–14959.

Bodyanskiy, Y., & Vynokurov, D. (2012). Modified probabilistic neuro-fuzzy network for text document classification. Automatic Control and Computer Sciences, 46(8), 346–353.

Fitri, M. H., Ishak, I., & Mahayuddin, N. A. (2024). Text normalization approach for noisy Malay-English social media texts. Malaysian Journal of Computer Science, 37(1), 12–22.

Han, B., Cook, P., & Baldwin, T. (2012). Automatically constructing a normalisation dictionary for microblogs. Proceedings of the 2012 Joint Conference on Empirical Methods in Natural Language Processing and Computational Natural Language Learning, 421–432.

Jang, J.-S. R. (1993). ANFIS: Adaptive-network-based fuzzy inference system. IEEE Transactions on Systems, Man, and Cybernetics, 23(3), 665–685.

Kumar, S., Dandapat, S., & Bhattacharyya, P. (2020). Robustness of deep learning models for NLP: A survey. arXiv preprint arXiv:2007.07393.

Liu, Q., Xie, X., Zhou, M., & Wang, Y. (2024). Fuzzy logic and natural language processing: A survey of hybrid techniques. Journal of Artificial Intelligence Research, 71, 113–145.

Rustamov, S. R. (2013). Neuro-fuzzy modeling of text sentiment analysis. Scientific Journal of Informatics, 14(1), 35–43.

Specht, D. F. (1990). Probabilistic neural networks. Neural Networks, 3(1), 109–118.

Subramaniam, L. V., et al. (2009). Challenges in processing noisy text. Proceedings of the ACL-IJCNLP 2009 Conference Short Papers, 127–130.

Taghva, K., Borsack, J., & Condit, A. (2000). Effects of OCR errors on document image retrieval. Information Processing & Management, 36(4), 725–740.

Vashishtha, S., & Susan, S. (2021). MultiLexANFIS: A neuro-fuzzy approach to social media sentiment analysis. Expert Systems with Applications, 183, 115357.

Wu, Y., et al. (2016). Cleaning as a service: A framework for online text normalization. Proceedings of the 25th International Conference on World Wide Web, 271–282.

Wu, S. (2022). Neural fuzzy logic reasoning for natural language inference. Proceedings of the 60th Annual Meeting of the Association for Computational Linguistics, 5234–5245.