Ashwini Garole,
Rohit Valsetwar,
Ganesh Sapani,
Atul Thakur,
Kunal Bombe,
- Professor Department of Computer science and engineering, Vishwaniketan’s Institute of Management Entrepreneurship and Engineering Technology (ViMEET), Khalapur Maharashtra India
- Student Department of Computer science and engineering, Vishwaniketan’s Institute of Management Entrepreneurship and Engineering Technology (ViMEET), Khalapur Maharashtra India
- Student Department of Computer science and engineering, Vishwaniketan’s Institute of Management Entrepreneurship and Engineering Technology (ViMEET), Khalapur Maharashtra India
- Student Department of Computer science and engineering, Vishwaniketan’s Institute of Management Entrepreneurship and Engineering Technology (ViMEET), Khalapur Maharashtra India
- Student Department of Computer science and engineering, Vishwaniketan’s Institute of Management Entrepreneurship and Engineering Technology (ViMEET), Khalapur Maharashtra India
Abstract
The Hindi Poetry Generator project represents a pioneering initiative in the domain of computational creativity, blending machine learning algorithms and natural language processing methodologies to craft poetic expressions in the Hindi language. Rooted in the vast landscape of Hindi literature, this project harnesses the power of deep learning models to generate evocative and culturally significant poetry.
At its core, the system relies on neural networks and sophisticated language modeling techniques to grasp the intricacies of Hindi poetic structures, including rhyme schemes, meter, and thematic elements. By training these models on a diverse corpus of Hindi poetry, the project achieves a level of understanding that enables it to craft verses that resonate deeply with readers, capturing the essence of Hindi literary traditions while also exploring new creative horizons.
The fusion of artificial intelligence with creative expression in this project opens up exciting possibilities for computational creativity in poetry. Through the iterative process of training and fine-tuning, the system refines its ability to generate poetry that not only adheres to established conventions but also pushes boundaries and introduces innovative poetic forms and themes. This adaptive approach ensures that the generated poetry maintains a balance between tradition and innovation, appealing to a wide range of audiences.
Furthermore, the project explores the potential of transfer learning and reinforcement learning techniques to enhance the quality and diversity of generated poetry. By leveraging pre-trained models such as GPT-3 and incorporating context-aware generation strategies, the system can produce poems that reflect a deep understanding of context and thematic nuances.
In summary, the Hindi Poetry Generator project showcases the transformative potential of artificial intelligence in the realm of creative writing, offering a glimpse into a future where machines collaborate with human creativity to produce compelling and culturally resonant literary works in languages as rich and expressive as Hindi.
Keywords: AI-driven poetry generation, Natural language processing (NLP), Generative models, Neural networks, Hindi poetry, Creative writing, Language models, Transformer-based architectures, GPT-3, Fine-tuning, Attention mechanisms, Recursive neural networks, Context-aware generation.
[This article belongs to Recent Trends in Programming languages(rtpl)]
References
[1] Bafna P, Saini JR. Hindi poetry classification using eager supervised machine learning algorithms. In2020 International Conference on Emerging Smart Computing and Informatics (ESCI) 2020 Mar 12 (pp. 175-178). IEEE.
[2] Kaur J, Saini JR. Automatic Punjabi poetry classification using machine learning algorithms with reduced feature set. International Journal of Artificial Intelligence and Soft Computing. 2016;5(4):311-9.
[3] Gangemi A, Sagri MT, Tiscornia D. Metadata for content description in legal information. InProcs. of LegOnt Workshop on Legal Ontologies 2003 Jan (Vol. 67).
[4] Hamidi S, Razzazi F, Ghaemmaghami MP. Automatic meter classification in Persian poetries using support vector machines. In2009 IEEE International Symposium on Signal Processing and Information Technology (ISSPIT) 2009 Dec 14 (pp. 563-567). IEEE.
[5] Z.-S. He, W.-T. Liang, L.-Y. Li, and Y.-F. Tian, “SVM- Based Classification Method for Poetry Style,” IEEE Xplore, 01-Aug-2007. [Online]. Available: https://ieeexplore.ieee.org/document/4370650
[6] Singh, A., & Jha, D. (2023). A neural network model for Hindi poetry generation. In Proceedings of the 2023 International Conference on Computational Linguistics and Intelligent Text Processing (CICLing) (pp. 123-134).
[7] J. Kaur and J. R. Saini, “A Study and Analysis of Opinion Mining Research in Indo-Aryan, Dravidian and Tibeto-Burman Language Families,” Indian Journals, vol. 4, no. 2, 2014
[8 Venugopal-Wairagade G, Saini JR, Pramod D. Novel language resources for Hindi: an aesthetics text corpus and a comprehensive stop lemma list. arXiv preprint arXiv:2002.00171. 2020 Feb 1.
[9] Yu, X., Tungare, M., Fan, W., Pérez-Quiñones, M., Fox, E.A., Cameron, W. and Cassel, L., 2007. Using automatic metadata extraction to build a structured syllabus repository. In Asian Digital Libraries. Looking Back 10 Years and Forging New Frontiers: 10th International Conference on Asian Digital Libraries, ICADL 2007, Hanoi, Vietnam, December 10-13, 2007. Proceedings 10 (pp. 337-346). Springer Berlin Heidelberg.
[10] Alsharif O, Alshamaa D, Ghneim N. Emotion classification in Arabic poetry using machine learning. International Journal of Computer Applications. 2013 Jan 1;65(16).
[11] Kulkarni A, Huet G. Sanskrit Computational Linguistics 3. InThird International Symposium, Hyderabad, India 2009 Jan 15.
[12] Joshi BK, Kushwah KK. A novel approach to automatic detection of Chaupai Chhand in Hindi poems. In2018 International Conference on Computing, Power and Communication Technologies (GUCON) 2018 Sep 28 (pp. 223-228). IEEE.
[13] Kushwah KK, Joshi BK. Rola: an equi-matrik chhand of Hindi poems. International Journal of Computer Science and Information Security. 2017 Mar;15(3), 362–5).
[14] Kaur J, Saini JR. PuPoCl: Development of Punjabi Poetry Classifier Using Linguistic Features and Weighting. INFOCOMP: Journal of Computer Science. 2017 Jun 1;16.
[15] Saini JR, Kaur J. Kāvi: An annotated corpus of punjabi poetry with emotion detection based on ‘navrasa’. Procedia Computer Science. 2020 Jan 1;167:1220-9.
[16] Bafna PB, Saini JR. Hindi Verse Class Predictor using Concept Learning Algorithms. In2020 2nd International Conference on Innovative Mechanisms for Industry Applications (ICIMIA) 2020 Mar 5 (pp. 318-322). IEEE.
[17] Jiang P, Ergu D, Liu F, Cai Y, Ma B. A Review of Yolo algorithm developments. Procedia computer science. 2022 Jan 1;199:1066-73.
Recent Trends in Programming languages
| Volume | 11 |
| Issue | 02 |
| Received | May 7, 2024 |
| Accepted | June 13, 2024 |
| Published | July 10, 2024 |