Abstract

Named Entity Recognition (NER) is the task of identifying the entities in the text document and categorize them into pre-defined categories such as Person, Location, Organization, etc. It is an important step in the processing of natural text. This paper propose an NER system for Sanskrit language using ontology. In contrast to modern languages, the Sanskrit language has rich morphology, complex compounds and vast use of epithets (descriptive titles, alternative names) which makes entity identification more difficult. To address this problem, we proposed a Model that combines linguistic preprocessing and ontology-aware entity linking to ensure robust recognition of relationship between NEs in Sanskrit text.

References

• Kale, S., & Govilkar, S. (2017). Survey of named entity recognition techniques for various indian regional languages. International Journal of Computer Applications, 164(4), 37-43.
• Joseph Mickole James, Sangeetha Jamal : Named Entity Recognition in Sanskrit : A Survey.
• Prakash Hiremath, S. B. (2014). Approaches to named entity recognition in indian languages: A study. International Journal of Engineering and Advanced Technology (IJEAT), ISSN, 2249, 8958.
• Patil, N., Patil, A. S., & Pawar, B. V. (2016). Survey of named entity recognition systems with respect to Indian and foreign languages. International Journal of Computer Applications, 134(16).
• Nanda, M. (2014). The named entity recognizer framework. International Journal of Innovative Research in Advanced Engineering, 1(4), 104-108.
• Singh, U., Goyal, V., & Lehal, G. S. (2012, December). Named entity recognition system for Urdu. In Proceedings of COLING 2012 (pp. 2507-2518).
• Kulkarni, I., Tikkal, S., Chaware, S., Kharate, P., & Pandit, A. (2022, February). Proposed Design to Recognize Ancient Sanskrit Manuscripts with Translation Using Machine Learning. In Proceedings of the International Conference on Innovative Computing & Communication (ICICC).
• Anonymous (2024). Mahanama : An Epic Literary Dataset For Entity Linking and Named Entity Coreference
• Syafiq, M. I., Talib, M. S., Salim, N., Haron, H., & Alwee, R. (2019, August). A concise review of named entity recognition system: Methods and features. In IOP Conference Series: Materials Science and Engineering (Vol. 551, No. 1, p. 012052). IOP Publishing.
• Srivastava, A., & Rajaraman, V. (2002). Computer recognition of Sanskrit-based Indian names. IEEE transactions on systems, man, and cybernetics, 21(1), 287-290.
• Bajwa, K. S., & Kaur, A. (2015). Hybrid approach for named entity recognition. International Journal of Computer Applications, 118(1).
• Castillo, J. M., Mateo, M. A. L., Paras, A. D., Sagum, R. A., & Santos, V. D. F. (2013). Named entity recognition using support vector machine for Filipino text documents. International Journal of Future Computer and Communication, 2(5), 530.
• Sasidhar, B., Yohan, P. M., Babu, A. V., & Govardhan, A. (2011). Named entity recognition in telugu language using language dependent features and rule based approach. International Journal of Computer Applications, 22(8), 30-34.
• Chopra, D., Jahan, N., & Morwal, S. (2012). Hindi named entity recognition by aggregating rule based heuristics and hidden markov model. International Journal of Information, 2(6), 43-52.
• Shah, H., Bhandari, P., Mistry, K., Thakor, S., Patel, M., & Ahir, K. (2016). Study of named entity recognition for indian languages. Int. J. Inf, 6(1), 11-25.
• Melinamath, B. C. (2014). Rule based methodology for recognition of Kannada named entities. Int. J. Latest Trends Eng. Technol.(IJLTET), 3, 50-58.
• Sujoy, S., Krishna, A., & Goyal, P. (2023, January). Pre-annotation based approach for development of a Sanskrit named entity recognition dataset. In Proceedings of the Computational Sanskrit & Digital Humanities: Selected papers presented at the 18th World Sanskrit Conference (pp. 59-70).
• V N Jokhakar, A survey on machine translation for Sanskrit Language to English Language,IDEES - International Multidisciplinary Research Journal 6 (2), 184-191.
• Gayen, V., & Sarkar, K. (2014). An HMM based named entity recognition system for indian languages: the JU system at ICON 2013. arXiv preprint arXiv:1405.7397.
• Ajees, A. P., & Idicula, S. M. (2018). A named entity recognition system for Malayalam using neural networks. Procedia computer science, 143, 962-969.