Spellbound Kannada: Harnessing Conditional Generative Adversarial Networks for Transformative Word Suggestion Systems in Kannada Language Processing
DOI:
https://doi.org/10.4108/eetiot.7792Keywords:
Natural Language Processing, Word Suggestion System, Conditional Generative Adversarial Network, Kannada, LSTMAbstract
INTRODUCTION: The advancement of a word suggestion system model is driven by the need to enhance user interaction and efficiency in digital communication. Hence, the word suggestion system helps minimize typographical errors and spelling mistakes. Therefore, various traditional methods are used to suggest words to sentences; however, these traditional models are extremely time consuming, prone to errors and tedious. METHODS: Owing to these factors, the present paper focuses on developing a Kannada word suggestion system using cGAN (Conditional Generative Adversarial Networks), as this system is designed to significantly enhance user interaction by offering predictive text suggestions in the Kannada language. RESULTS: The training dataset, which resides on AWS S3, comprises a comprehensive collection of Kannada texts utilized for both training and validation purposes. Furthermore, the implementation of the model leverages the TensorFlow and keras framework, specifically employing long short-term memory (LSTM) networks for effective sequence prediction and generation. LSTMs are particularly advantageous in NLP processing because they can capture long-term dependencies within sequential data. To facilitate user interaction, a web-based interface has been developed using Flask, enabling users to input initial characters and receive dynamically generated Kannada word suggestions. CONCLUSION: This paper not only delves into the application of cGANs within the realm of NLP but also illustrates practical deployment strategies utilizing cloud services and modern web technologies. Overall, the proposed approaches demonstrate the potential of the cGAN in enhancing the user experience through intelligent text prediction systems tailored for the Kannada language.
Downloads
References
[1] Goswami, B., Bhavsar, N., Alzobidy, S. A., Lavanya, B., Udhayakumar, R., & Rajapandian, K. (2025). Sentiment Analysis Using Natural Language Processing. Natural Language Processing for Software Engineering, 283-294.
[2] Esfahani, M. N. (2024). Content Analysis of Textbooks via Natural Language Processing. American Journal of Education and Practice, 8(4), 36-54.
[3] Dong, J. (2024). Natural Language Processing Pretraining Language Model for Computer Intelligent Recognition Technology. ACM Transactions on Asian and Low-Resource Language Information Processing, 23(8), 1-12.
[4] Perera, S. S., & Sumanathilaka, D. K. (2025, January). Machine Translation and Transliteration for Indo-Aryan Languages: A Systematic Review. In Proceedings of the First Workshop on Natural Language Processing for Indo-Aryan and Dravidian Languages (pp. 11-21).
[5] Shukla, K., Vashishtha, E., Sandhu, M., & Choubey, P. R. (2023). Natural Language Processing: Unlocking the Power of Text and Speech Data. Xoffencerpublication.
[6] Stanisz, T., Drożdż, S., & Kwapień, J. (2024). Complex systems approach to natural language. Physics Reports, 1053, 1-84.
[7] Anitha, G., Kumar, G. S., Swamy, B. M., Thriveni, J., & Venugopal, K. R. (2021). Kannada morphological analyser and generator using natural language processing and ML approaches. Turkish Journal of Computer and Mathematics Education, 12(11), 2826-2838.
[8] Irani, M., Elahimanesh, M. H., Ghafouri, A., & Bidgoli, B. M. (2022, December). A Supervised Deep Learning-based Approach for Bilingual Arabic and Persian Spell Correction. In 2022 8th Iranian Conference on Signal Processing and Intelligent Systems (ICSPIS) (pp. 1-7). IEEE.
[9] Phukan, R., Neog, M., Goutom, P. J., & Baruah, N. (2024). Automated Spelling Error Detection in Assamese Texts using Deep Learning Approaches. Procedia Computer Science, 235, 1684-1694.
[10] Jim, J. R., Talukder, M. A. R., Malakar, P., Kabir, M. M., Nur, K., & Mridha, M. F. (2024). Recent advancements and challenges of NLP-based sentiment analysis: A state-of-the-art review. Natural Language Processing Journal, 100059.
[11] Aithal, S. R., Sn, M., Ganiga, R., Rao B, A., & Hegde K, G. (2024). KannadaLex: A lexical database with psycholinguistic information. ACM Transactions on Asian and Low-Resource Language Information Processing, 23(7), 1-21.
[12] Prasad, C., Kallimani, J. S., Reddy, G., & Dhanashekar, K. (2025). Developing spell check and transliteration tools for Indian regional language–Kannada. In Applied Data Science and Smart Systems (pp. 152-161). CRC Press.
[13] Lubis, Y., Ramadhany, C. A., Widyana, A., Mahara, E. F., & Sarahseti, D. F. (2024). The Role of Vowels and Consonants In English Language Learning. Socius: Jurnal Penelitian Ilmu-Ilmu Sosial, 1(11).
[14] Singh, S., & Singh, S. (2021). HINDIA: a deep-learning-based model for spell-checking of Hindi language. Neural Computing and Applications, 33(8), 3825-3840.
[15] Abdullaev, I., Prodanova, N., Ahmed, M. A., Lydia, E. L., Shrestha, B., Joshi, G. P., & Cho, W. (2023). Leveraging metaheuristics with artificial intelligence for customer churn prediction in telecom industries. Electronic Research Archive, 31(8).
[16] Abandah, G. A., Suyyagh, A., & Khedher, M. Z. (2021). Correcting arabic soft spelling mistakes using bilstm-based machine learning. arXiv preprint arXiv:2108.01141.
[17] Kasmaiee, S., Kasmaiee, S., & Homayounpour, M. (2023). Correcting spelling mistakes in Persian texts with rules and deep learning methods. Scientific reports, 13(1), 19945.
[18] Caryappa, B. C., Hulipalled, V. R., & Simha, J. B. (2020, October). Kannada grammar checker using LSTM neural network. In 2020 International Conference on Smart Technologies in Computing, Electrical and Electronics (ICSTCEE) (pp. 332-337). IEEE.
[19] Murthy, S. R., Akshatha, A. N., Upadhyaya, C. G., & Kumar, P. R. (2017, September). Kannada spell checker with sandhi splitter. In 2017 International Conference on Advances in Computing, Communications and Informatics (ICACCI) (pp. 950-956). IEEE.
[20] Dashti, S. M. S., Khatibi Bardsiri, A., & Jafari Shahbazzadeh, M. (2024). PERCORE: A deep learning-based framework for persian spelling correction with phonetic analysis. International Journal of Computational Intelligence Systems, 17(1), 114.
[21] Phukan, R., Baruah, N., Sarma, S. K., & Konwar, D. (2024). Exploring Character-Level Deep Learning Models for POS Tagging in Assamese Language. Procedia Computer Science, 235, 1467-1476.
[22] Zaky, D., & Romadhony, A. (2019, September). An LSTM-based spell checker for indonesian text. In 2019 international conference of advanced informatics: concepts, theory and applications (ICAICTA) (pp. 1-6). IEEE.
[23] Ji, T., Yan, H., & Qiu, X. (2021, November). SpellBERT: A lightweight pretrained model for Chinese spelling check. In Proceedings of the 2021 conference on empirical methods in natural language processing (pp. 3544-3551).
[24] Aziz, R., Anwar, M. W., Jamal, M. H., & Bajwa, U. I. (2021). A hybrid model for spelling error detection and correction for Urdu language. Neural Computing and Applications, 33, 14707-14721.
[25] Kasmaiee, S., Kasmaiee, S., & Homayounpour, M. (2023). Correcting spelling mistakes in Persian texts with rules and deep learning methods. Scientific reports, 13(1), 19945.
[26] Kaur, G., Kaur, K., & Singh, P. (2019, March). Spell checker for Punjabi language using deep neural network. In 2019 5th international conference on advanced computing & communication systems (ICACCS) (pp. 147-151). IEEE.
[27] Ahmadzade, A., & Malekzadeh, S. (2021). Spell correction for azerbaijani language using deep neural networks. arXiv preprint arXiv:2102.03218.
Downloads
Published
How to Cite
Issue
Section
License
Copyright (c) 2025 Prathibha R J, Anupama N, Sudarshan A S
This work is licensed under a Creative Commons Attribution-NonCommercial-ShareAlike 4.0 International License.
This is an open-access article distributed under the terms of the Creative Commons Attribution CC BY 3.0 license, which permits unlimited use, distribution, and reproduction in any medium so long as the original work is properly cited.
