AI Hindi Poem Generator

Year : 2024 | Volume : 11 | Issue : 02 | Page : 10-16
    By

    Ashwini Garole,

  • Rohit Valsetwar,

  • Ganesh Sapani,

  • Atul Thakur,

  • Kunal Bombe,

  1. Professor, Department of Computer Science and Engineering, Vishwaniketan’s Institute of Management Entrepreneurship and Engineering Technology (ViMEET), Khalapur, Maharashtra, India
  2. Student, Department of Computer Science and Engineering, Vishwaniketan’s Institute of Management Entrepreneurship and Engineering Technology (ViMEET), Khalapur, Maharashtra, India
  3. Student, Department of Computer Science and Engineering, Vishwaniketan’s Institute of Management Entrepreneurship and Engineering Technology (ViMEET), Khalapur, Maharashtra, India
  4. Student, Department of Computer Science and Engineering, Vishwaniketan’s Institute of Management Entrepreneurship and Engineering Technology (ViMEET), Khalapur, Maharashtra, India
  5. 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 ]

How to cite this article:
Ashwini Garole, Rohit Valsetwar, Ganesh Sapani, Atul Thakur, Kunal Bombe. AI Hindi Poem Generator. Recent Trends in Programming languages. 2024; 11(02):10-16.
How to cite this URL:
Ashwini Garole, Rohit Valsetwar, Ganesh Sapani, Atul Thakur, Kunal Bombe. AI Hindi Poem Generator. Recent Trends in Programming languages. 2024; 11(02):10-16. Available from: https://journals.stmjournals.com/rtpl/article=2024/view=155892



References

  1. Bafna P, Saini JR. Hindi poetry classification using eager supervised machine learning algorithms. In 2020 IEEE International Conference on Emerging Smart Computing and Informatics (ESCI). 2020 Mar 12; 175–178.
  2. Kaur J, Saini JR. Automatic Punjabi poetry classification using machine learning algorithms with reduced feature set. Int J Artif Intell Soft Comput. 2016; 5(4): 311–9.
  3. Sagri MT, Tiscornia D. Metadata for content description in legal information. 14th International Workshop on Database and Expert Systems Applications, 2003. Proceedings., Prague, Czech Republic, 2003, p. 745–749. doi: 10.1109/DEXA.2003.1232110.
  4. Hamidi S, Razzazi F, Ghaemmaghami MP. Automatic meter classification in Persian poetries using support vector machines. In 2009 IEEE International Symposium on Signal Processing and Information Technology (ISSPIT). 2009 Dec 14; 563–567.
  5. He Z-S, Liang W-T, Li L-Y, Tian Y-F. SVM-Based Classification Method for Poetry Style. IEEE Xplore, 2007 International Conference on Machine Learning and Cybernetics, Hong Kong, 2007 Aug 01; 2936–2940. [Online]. Available: https://ieeexplore.ieee.org/document/4370650
  6. Singh A, Jha D. A neural network model for Hindi poetry generation. In Proceedings of the 2023 International Conference on Computational Linguistics and Intelligent Text Processing (CICLing). 2023; 123–134.
  7. Jiang P, Ergu D, Liu F, Cai Y, Ma B. A Review of Yolo algorithm developments. Procedia Comput Sci. 2022 Jan 1; 199: 1066–73.
  8. Kaur J, Saini JR. A Study and Analysis of Opinion Mining Research in Indo-Aryan, Dravidian and Tibeto-Burman Language Families. Indian Journals: International Journal of Data Mining and Emerging Technologies. 2014; 4(2): 53–60.
  9. 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.
  10. Yu X, Tungare M, Fan W, Pérez-Quiñones M, Fox EA, Cameron W, Cassel L. 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. Berlin Heidelberg: Springer; 2007; 337–346.
  11. Alsharif O, Alshamaa D, Ghneim N. Emotion classification in Arabic poetry using machine learning. Int J Comput Appl. 2013 Jan 1; 65(16): 10–15.
  12. Kulkarni A, Huet G. Sanskrit Computational Linguistics 3. In 3rd International Symposium, Hyderabad, India. 2009 Jan 15.
  13. Joshi BK, Kushwah KK. A novel approach to automatic detection of Chaupai Chhand in Hindi poems. In 2018 IEEE International Conference on Computing, Power and Communication Technologies (GUCON). 2018 Sep 28; 223–228.
  14. Kushwah KK, Joshi BK. Rola: an equi-matrik chhand of Hindi poems. Int J Comput Sci Inf Secur. 2017 Mar; 15(3): 362–5.
  15. Kaur J, Saini JR. PuPoCl: Development of Punjabi Poetry Classifier Using Linguistic Features and Weighting. INFOCOMP: J Comput Sci. 2017 Jun 1; 16(1–2): 1–7.
  16. Saini JR, Kaur J. Kāvi: An annotated corpus of punjabi poetry with emotion detection based on ‘navrasa’. Procedia Comput Sci. 2020 Jan 1; 167: 1220–9.
  17. Bafna PB, Saini JR. Hindi Verse Class Predictor using Concept Learning Algorithms. In 2020 IEEE 2nd International Conference on Innovative Mechanisms for Industry Applications (ICIMIA). 2020 Mar 5; 318–322.
Regular Issue Subscription Review Article
Volume 11
Issue 02
Received 07/05/2024
Accepted 13/06/2024
Published 10/07/2024
Total Visits: 782


My IP

PlumX Metrics