Leveraging formal languages and automata theory in natural language processing (NLP)

Gambhire, Smita; Panhalkar, Archana R.; Patil, Dipali Himmatrao; Kedar, Seema; Kumar, Malayaj; Panchal, Brijeshkumar Y.

doi:10.47974/JDMSC-2552

Open Access Research Article

Leveraging formal languages and automata theory in natural language processing (NLP)

Smita Gambhiresmitagambhire@csmu.ac.inDepartment of Computer Science & Information TechnologyChhatrapati Shivaji Maharaj UniversityNavi Mumbai, Maharashtra, 410206, IndiaView full profile → , ^*Archana R. PanhalkarCorresponding authorarchana10bhosale@rediffmail.comDepartment of Artificial Intelligence & Data ScienceAmrutvahini College of EngineeringSangamner, Maharashtra, 422608, IndiaView full profile → , Dipali Himmatrao Patilpatil.dipali07@gmail.comDepartment of Information TechnologyJSPM’s Rajarshi Shahu College of EngineeringPimpri-Chinchwad, Maharashtra, 411033, IndiaView full profile → , Seema Kedarsvkedar_comp@jspmrscoe.edu.inDepartment of Computer EngineeringJSPM’s Rajarshi Shahu College of EngineeringPimpri-Chinchwad, Maharashtra, 411033, IndiaView full profile → , Malayaj Kumarkumarmalayaj@gmail.comDepartment of Computer EngineeringIndira College of Engineering and ManagementPune, Maharashtra, 410506, IndiaView full profile → , Brijeshkumar Y. Panchalpanchalbrijesh02@gmail.comDepartment of Computer EngineeringSardar Vallabhbhai Patel Institute of Technology (SVIT), Anand DistrictGujarat Technological University (GTU)Vasad, Gujarat, 388306, IndiaView full profile →

* Corresponding author · click or hover a name for details

pp. 995–1004Vol. 29Issue 2-BFebruary 2026DOI: 10.47974/JDMSC-2552 Crossmark XML

Received:: 06 May 2025
Published Online:: 18 Feb 2026
Article type:: Research Article
Language:: EN
Article no.:: JDMSC-2552
Pages:: 995–1004

Abstract

Formal languages and automata theory are very important for handling and understanding real languages. This paper discuss about basic automata models, such as finite automata and finite-state transducers, and how they can be used in morphological analysis, tokenization, and lexical analysis. The paper also focuses how these old techniques can be combined with natural language processing methods. In particular, it focusses on mixed models that use automata theory and machine learning to make things more accurate and quick. The part automata theory plays in formal checking and explaining NLP models is also looked at, shows how important it is for making systems that are clear and dependable.

Keywords

Formal languages Automata theory Lexical analysis Machine learning integration NLP explainability

Subject Classifications

31A1033E30

References

[1] Y. Zhang, “Syntactic and semantic properties of on the contrary in British university student essay writing: A corpus-based systemic functional analysis,” Appl. Sci., vol. 12, no. 10635 (2022).
[2] L. C. Chen, K. H. Chang, S. C. Yang, and S. C. Chen, “A corpus-based word classification method for detecting difficulty level of English proficiency tests,” Appl. Sci., vol. 13, no. 1699 (2023).
[3] C. D. Kokane, S. D. Babar, P. N. Mahalle, and S. P. Patil, “Word sense disambiguation: Mathematical modelling of adaptive word embedding technique for word vector,” J. Interdiscip. Math., vol. 26, no. 3, pp. 475–482 (2023).
[4] C. L. Lin, C. L. Fan, and B. K. Chen, “Hybrid analytic hierarchy process–artificial neural network model for predicting the major risks and quality of Taiwanese construction projects,” Appl. Sci., vol. 12, no. 7790 (2022).
[5] V. Khetani, Y. Gandhi, and R. R. Patil, “A study on different sign language recognition techniques,” in Proc. Int. Conf. Comput., Commun. Green Eng. (CCGE), Pune, India, pp. 1–4 (2021).
[6] Gajanand Sharma, Naveen Hemrajani, Satyajeet Sharma, Aditya Upadhyay, Yogesh Bhardwaj, and Ashutosh Kumar, “Alzheimer disease progression forecasting: Empowering models through hybrid of CNN and LSTM with PSO optimization,” in Proc. Int. Conf. Emerg. Smart Comput. Informatics (ESCI), Pune, India, pp. 1–5 (2024).
[7] S. Al-Ghamdi, H. Al-Khalifa, and A. Al-Salman, “Fine-tuning BERT-based pre-trained models for Arabic dependency parsing,” Appl. Sci., vol. 13, no. 4225 (2023).
[8] Dharmesh Dhabliya, Jambi Ratna Raja Kumar, Anish Kumar Dhablia, Ritika Dhabliya, Sharayu Ikhar, Vinit Khetani, and Ahmed Alkhayyat, “An advantage actor-critic and proximal policy optimization model for adaptive scheduling of heterogeneous cloud workloads,” Math. Model. Eng. Probl., vol. 11, no. 8, pp. 2275–2284 (2024).
[9] V. D. Gowda, N. Suganthi, V. N. Prasad, M. Tarambale, P. S. V. V. S. R. Kumar, and A. Muthusamy, “Implementing secure cryptographic protocols in 5G and 6G networks,” Journal of Discrete Mathematical Sciences and Cryptography, vol. 28, no. 5-A, pp. 1505–1515 (2025), doi: 10.47974/JDMSC-2149.
[10] Gajanand Sharma, Naveen Hemrajani, Satyajeet Sharma, Aditya Upadhyay, Yogesh Bhardwaj, and Ashutosh Kumar, “Data management framework for IoT edge-cloud architecture for resource-constrained IoT application,” Journal of Discrete Mathematical Sciences and Cryptography, vol. 25, no. 4, pp. 1093–1103 (2022).
[11] M. A. Palomino and F. Aider, “Evaluating the effectiveness of text pre-processing in sentiment analysis,” Appl. Sci., vol. 12, no. 8765 (2022).
[12] K. N. Aaglave, D. S. Tanaji, K. G. Yogesh, K. V. Jotiba, and R. V. Ravindra, “A global survey of diploma education: Trends, challenges, and future prospects,” Int. J. Adv. Comput. Theory Eng., vol. 13, no. 2, pp. 14–20 (Mar. 2025).

Views: 297Downloads: 130Citations: 1