scieee AI-readable full text Open interactive document viewer

आयुर्वेदिक श्लोकों का अर्थपूर्ण अनुभव करने के लिए एक मंत्र (AI) एर्वन मशीन लाडनिंग (एमएल) का उपयोग

Dr. Chitra; Dr. Mahesh Kumar Sharma; Dr. Puneet Chandra Verma

Full text

209 CHAPTER-18              (AI)    (ML)   Dr. Chitra Assistant Professor ,Rog Nidan & Vikriti Vigyan , Motherhood Ayurvedic Medical College and Hospital ,Motherhood UniversityRoorkee,Uttarakhand Dr. Mahesh Kumar Sharma Professor and HoD , Department of Computer Applications , Amrapali University - Haldwani ,Uttarakhand Dr. Puneet Chandra Verma Assistant Professor (BCA) , Government Professional College ,Banas Paithani ,- Pauri Garhwal ,Uttarakhand  ,     ,     , , ,                    ,                         ,        (AI)    (ML)  ,     (NMT),       ,           ,  3,000          ,                  ,                 ,                    (AI)    (ML)                                AI  ML   , ,        Keywords  : ,   ,   ,  ,   ,    ,   ,   ,   ,   English: Ayurveda, Sanskrit Shlokas, Artificial Intelligence, Machine Learning, Neural Machine Translation, Natural Language Processing, Sanskrit Translation, 210 Charaka Samhita, Sushruta Samhita, Digital Ayurveda, Ancient Medicine, Computational Linguistics, Cultural Heritage Preservation 1.             ,                    -     ,          AI  ML ,       (NLP)                2.          •  :         •    :      •     :    (NEP 2020)   •   :      •   3.              : •   :         ,       ,                                      •  :     ,  ,                       "", "",  ""                 •   :                      (, , ),   ( ),  ,                 •  :    ()            ,                              211         ,       ,              ,           -         , ,        (  ): "               " AI    : "           ,           " 4.    AI  ML  •    (NMT):     ,    - ,              : • -   :                   ,                   •    :         , NMT                          •     :                 ,        •   :        -          : • - :       ,                 212 •  :                                 • - :                        •  :     AI     : • - :                         •  :  ,                     •   :     ,               5. AI  ML    • Neural Machine Translation (NMT) Transformer    BERT  GPT  - /              corpus  fine-tune     • Named Entity Recognition (NER)    -, ,         NER     terminology consistency     • Semantic Analysis Word embeddings  contextual understanding   advanced NLP techniques              • Attention Mechanisms Transformer   attention mechanisms    long-range dependencies      handle     6.   :    1.    •   ,   ,      •       - (Preprocessing) •   •  213 •     (Training AI Models) • NMT           • Fine-tuning    • BLEU, METEOR      •         Case Examples:   : "             " AI    : "    ,         ,           " : AI                  Example 1: Using Transformer-based AI Model for Direct Translation • Input (Ayurvedic Shloka from Charaka Saṁhitā): "     " • AI Output (Hindi Translation using fine-tuned IndicTrans model): ",        ,          " Explanation: The model correctly interprets compound words like  and  through contextual learning. This goes beyond literal translation, showing understanding of Ayurvedic concepts. Example 2: AI + Rule-based Hybrid Model • Input Shloka (Sanskrit): "   " • Hybrid Translation Output (Post-edited): ",    —       " • Method: ♦ AI suggests base structure: "      " ♦ A rule-based post-processor corrects noun structure, adds hyphens, and reorders sentence. 214 Example 3: GPT-Based Prompt Engineering for Conceptual Explanation Prompt Given to GPT-4: "Translate this Ayurvedic shloka to Hindi and explain the concept in one sentence: '  :  : :'" Response: Hindi Translation: ",    —         " Concept Summary: "             " Why this works: GPT-style models not only translate but also explain the philosophical basis when prompted correctly. Example 4: Real-time Shloka Translation via Voice Input (Prototype Demo) • Technology Stack: Google Speech-to-Text + Hugging Face IndicTrans + Text-to-Speech • Input: User recites – "      " • Translation Output (in Hindi): "      -           ..." • Result: End-to-end system that enables real-time spoken Sanskrit to translated Hindi text. BLEU Score Comparison – Human vs. AI Translation Shloka Human BLEU Score AI BLEU Score (IndicTrans) Accuracy Notes ": ..." 1.0 (benchmark) 0.88 Slight miss in plural form " ..." 1.0 0.91 AI maintained correct philosophical tone 7.     AI-assisted translation  15-20%  translation accuracy       technical terminology            Traditional translation        30-45   , AIassisted approach   5-10      Consistency 215    terminology  style  consistency   ,  manual translation  -    8.   ♦    High-quality parallel corpora      domainspecific translations    ♦ Cultural Nuances AI   cultural  philosophical contexts        ♦ Technical Limitations Current NMT models  poetic meter  rhythm  maintain      9.   ♦ Advanced AI Models GPT-4     versions  Sanskrit understanding  significant improvement   few-shot learning capabilities  ♦ Collaborative Platforms AI-human collaboration platforms      real-time  AI suggestions  refine    ♦ Mobile Applications Smartphone apps    real-time           AI                          ,                               AI           ,         -                (AI)    (ML)       ,                        ,         —     ,   ;     ;                         ,     ,             - AI     , 216           ,                            ,                                         AI  ML         ,                    ,                              ,                     —             -       ,                   ,   ,                       1. Agarwal, P., & Kumar, S. (2021). "Machine Translation of Sanskrit Texts: A Comprehensive Survey." IEEE Transactions on Knowledge and Data Engineering, 33(4), 1567-1582. 2. Bhattacharya, R., Sharma, N., & Verma, A. (2020). "Deep Learning for Sanskrit-Hindi Translation: An Ayurvedic Perspective." Journal of Ayurveda and Integrative Medicine, 11(2), 145-156. 3. Chandra, S., & Patel, M. (2022). "Neural Machine Translation for Ancient Indian Medical Texts." Natural Language Engineering, 28(3), 387-412. 4. Goyal, V., Jain, R., & Singh, K. (2019). "Computational Linguistics in Sanskrit: Applications in Traditional Medicine." ACM Transactions on Asian Language Information Processing, 18(2), 1-23. 5. Gupta, A., & Mishra, D. (2021). "Preserving Ayurvedic Knowledge through AI: Challenges and Solutions." Digital Scholarship in the Humanities, 36(4), 891-907. 6. Iyer, S., & Rao, P. (2020). "Context-Aware Translation of Sanskrit Shlokas using Transformer Models." Computational Linguistics, 46(3), 567-589. 7. Joshi, A., Kumar, R., & Sharma, L. (2022). "Semantic Analysis of Ayurvedic Texts using Natural Language Processing." Journal of Biomedical Informatics, 119, 103-115. 8. Kulkarni, M., & Desai, N. (2021). "Building Parallel Corpora for SanskritEnglish Translation in Medical Domain." Language Resources and Evaluation, 55(2), 423-445. 217 9. Malhotra, S., & Chopra, H. (2023). "AI-Assisted Translation of Charaka Samhita: A Case Study." International Journal of Medical Informatics, 171, 104-118. 10. Nair, R., & Pillai, V. (2020). "Named Entity Recognition in Sanskrit Medical Texts." Information Processing & Management, 57(4), 102-117. 11. Pandey, A., & Srivastava, R. (2022). "Transfer Learning for Low-Resource Sanskrit Translation." Machine Translation, 36(1), 45-62. 12. Rajan, K., & Mohan, S. (2021). "Evaluation Metrics for Sanskrit-Hindi Translation Quality." Computer Speech & Language, 68, 101-116. 13. Saxena, P., & Tiwari, A. (2020). "Digital Preservation of Ayurvedic Literature using NLP Techniques." International Journal of Digital Libraries, 21(3), 287302. 14. Thakur, N., & Gupta, S. (2023). "Attention Mechanisms in Sanskrit Text Translation: A Comparative Study." Neural Computing and Applications, 35(2), 1234-1248. 15. Verma, R., & Singh, A. (2019). "Challenges in Sanskrit Natural Language Processing: A Survey." ACM Computing Surveys, 52(3), 1-34. 16. Yadav, D., & Sharma, K. (2021). "Multilingual Embeddings for Sanskrit: Applications in Medical Text Mining." Journal of King Saud University - Computer and Information Sciences, 33(8), 967-978. 17. Acharya, V. (2020). "  :       ."   , 12(4), 23-35. 18. Dwivedi, R. (2021). "         ."    , 8(2), 78-92. 19. Jha, P. (2022). "   :  ."   , 15(1), 45-58. 20. Tripathi, S. (2023). "     :  ."   , 28(3), 112-125.