Translating Sanskrit to Hindi Language using Recurrent Neural Network (RNN)-L2 Regularization

Authors

  • Prashanth Kammar Department of Computer Science and Engineering, Proudhadevaraya institute of Technology, Hosapete, and Visvesvaraya Technological University, Belagavi, India
  • Parashuram Baraki Department of Computer Science & Engineering, Smt.Kamala and Sri Venkappa M Agadi College of Engineering and Technology, Laxmeshwar and Visvesvaraya Technological University, Belagavi, India
  • Sunil Kumar Ganganayaka Department of Computer Science and Engineering, University Visvesvaraya College of Engineering, Bengaluru, India
  • Manjunath Swamy Byranahalli Eraiah Department of Computer Science and Engineering, Don Bosco Institute of Technology, Bengaluru, and Visvesvaraya Technical University, Belagavi India
  • Kolakaluri Lakshman Arun Kumar Department of Computer Science and Engineering, KNS Institute of Technology, Bengaluru, and Visvesvaraya Technical University, Belagavi, India

Keywords:

Linguistic Feature Extraction, Machine Translation, Natural Language, Recurrent Neural Network, Rule-based system

Abstract

Machine Translation (MT) is a subfield of computer linguistics that focuses on the automatic translation from one natural language into another without any human involvement. There is a huge need for translating information between languages to send and communicate thoughts because native people interact in a variety of languages. However, Sanskrit is an ancient Indo-European language that requires essential processing to be explored in computer science and computational language analysis. In this paper, Recurrent Neural Network (RNN)-L2 regularization method is proposed for the Sanskrit to Hindi translation language. A neural machine translation system is trained using the linguistic information from the rule-based input. The proposed method is innovative and adaptable to any low-resource language with extensive morphology that covers multiple domains with minimal human involvement. The efficacy of the RNN-L2 regularization method is demonstrated by employing the dataset of Corpora. The existing methods such as machine translation systems, and hybrid machine translation systems are used to explain the efficacy of the RNN-L2 regularization method. The proposed RNN-L2 regularization method achieves better BLEU score, and METEOR of 76% and 72% compared with the existing methods such as machine translation systems, and hybrid machine translation systems.

Downloads

Download data is not yet available.

References

L. Benkova, D. Munkova, L. Benko, and M. Munk, “Evaluation of English–Slovak neural and statistical machine translation,” Applied Sciences, vol. 11, no. 7, p. 2948, Mar. 2021, https://doi.org/10.3390/app11072948.

K. D. Garg, S. Shekhar, A. Kumar, V. Goyal, B. Sharma, R. Chengoden, and G. Srivastava, “Framework for Handling Rare Word Problems in Neural Machine Translation System Using Multi-Word Expressions,” Applied Sciences, vol. 12, no. 21, p. 11038, Oct. 2022, https://doi.org/10.3390/app122111038.

S. Saini and V. Sahula, “Setting up a neural machine translation system for English to Indian languages,” in: Cognitive Informatics, Computer Modelling, and Cognitive Science, Academic Press, 2020, pp. 195-212, https://doi.org/10.1016/B978-0-12-819443-0.00011-8.

M. Brour, and A. Benabbou, “ATLASLang NMT: Arabic text language into Arabic sign language neural machine translation,” Journal of King Saud University-Computer and Information Sciences, vol. 33, no. 9, pp. 1121-1131, Nov. 2021, https://doi.org/10.1016/j.jksuci.2019.07.006.

J. X. Huang, K. S. Lee, and Y. K. Kim, “Hybrid translation with classification: Revisiting rule-based and neural machine translation,” Electronics, vol. 9, no. 2, p. 201, Jan. 2020, https://doi.org/10.3390/electronics9020201.

T. Khanna, J. N. Washington, F. M. Tyers, S. Bayatlı, D. G. Swanson, T. A. Pirinen, I. Tang, and H. Alòs i Font, “Recent advances in Apertium, a free/open-source rule-based machine translation platform for low-resource languages,” Mach. Transl., vol. 35, no. 4, pp. 475-502, Dec. 2021, https://doi.org/10.1007/s10590-021-09260-6.

L. H. Baniata, I. K. Ampomah, and S. Park, “A transformer-based neural machine translation model for Arabic dialects that utilizes subword units,” Sensors, vol. 21, no. 19, p. 6509, Sep. 2021, https://doi.org/10.3390/s21196509.

A. Srivastav and S. Singh, “Proposed model for context topic identification of english and hindi news article through LDA approach with NLP technique,” J. Inst. Eng. India Ser. B, pp. 1-7, Apr. 2022, https://doi.org/10.1007/s40031-021-00655-w.

E. L. Pontes, S. Huet, J. M. Torres-Moreno, and A. C. Linhares, “Compressive approaches for cross-language multi-document summarization,” Data & Knowledge Engineering, vol. 125, p. 101763, Jan. 2020, https://doi.org/10.1016/j.datak.2019.101763.

N. S. Khan, A. Abid, and K. Abid, “A novel natural language processing (NLP)–based machine translation model for English to Pakistan sign language translation,” Cognit. Comput., vol. 12, pp. 748-765, Jul. 2020, https://doi.org/10.1007/s12559-020-09731-7.

J.E. Ortega, R. Castro Mamani, and K. Cho, “Neural machine translation with a polysynthetic low resource language,” Mach. Transl., vol. 34, no. 4, pp. 325-346, Dec. 2020, https://doi.org/10.1007/s10590-020-09255-9.

D. Banik, A. Ekbal, P. Bhattacharyya, and S. Bhattacharyya, “Assembling translations from multi-engine machine translation outputs,” Appl. Soft Comput., vol. 78, pp. 230-239, May 2019, https://doi.org/10.1016/j.asoc.2019.02.031.

S. Thara and P. Poornachandran, “Transformer based language identification for Malayalam-english code-mixed text,” IEEE Access, vol. 9, pp. 118837-118850, Aug. 2021, https://doi.org/10.1109/ACCESS.2021.3104106.

S. Bhatia, A. Kumar, and M. M. Khan, “Role of genetic algorithm in optimization of Hindi word sense disambiguation,” IEEE Access, vol. 10, pp. 75693-75707, Jul. 2022, https://doi.org/10.1109/ACCESS.2022.3190406.

M. Singh, R. Kumar, and I. Chana, “Improving neural machine translation for low-resource Indian languages using rule-based feature extraction,” Neural Comput. Appl., vol. 33, pp. 1103-1122, Feb. 2021, https://doi.org/10.1007/s00521-020-04990-9.

J. Dugonik, M. Sepesy Maučec, D. Verber, and J. Brest, “Reduction of Neural Machine Translation Failures by Incorporating Statistical Machine Translation,” Mathematics, vol. 11, no. 11, p. 2484, May 2023, https://doi.org/10.3390/math11112484.

S. R. Laskar, A. Gogoi, S. Dutta, P. K. Adhikary, P. Nath, P. Pakray, and S. Bandyopadhyay, “Investigation of negation effect for English–Assamese machine translation,” Sādhanā, vol. 47, no. 4, p. 238, Nov. 2022, https://doi.org/10.1007/s12046-022-01965-5.

S. Dewangan, S. Alva, N. Joshi, and P. Bhattacharyya, “Experience of neural machine translation between indian languages,” Mach. Transl., vol. 35, no. 1, pp. 71-99, Apr. 2021, https://doi.org/10.1007/s10590-021-09263-3.

Sitender and S. Bawa, “A Sanskrit-to-English machine translation using hybridization of direct and rule-based approach”, Neural Comput. Appl., vol. 33, pp. 2819-2838, Apr. 2021, https://doi.org/10.1007/s00521-020-05156-3.

M. A. Islam, M. S. H. Anik, and A. A. A. Islam, “Towards achieving a delicate blending between rule-based translator and neural machine translator,” Neural Comput. Appl., vol. 33, pp. 12141-12167, Sep. 2021, https://doi.org/10.1007/s00521-021-05895-x.

Downloads

Published

24.03.2024

How to Cite

Kammar, P. ., Baraki, P. ., Ganganayaka, S. K. ., Byranahalli Eraiah, M. S., & Arun Kumar, K. L. . (2024). Translating Sanskrit to Hindi Language using Recurrent Neural Network (RNN)-L2 Regularization. International Journal of Intelligent Systems and Applications in Engineering, 12(3), 199–208. Retrieved from https://ijisae.org/index.php/IJISAE/article/view/5241

Issue

Vol. 12 No. 3 (2024)

Section

Research Article

License

Creative Commons License

This work is licensed under a Creative Commons Attribution-ShareAlike 4.0 International License.

All papers should be submitted electronically. All submitted manuscripts must be original work that is not under submission at another journal or under consideration for publication in another form, such as a monograph or chapter of a book. Authors of submitted papers are obligated not to submit their paper for publication elsewhere until an editorial decision is rendered on their submission. Further, authors of accepted papers are prohibited from publishing the results in other publications that appear before the paper is published in the Journal unless they receive approval for doing so from the Editor-In-Chief.

IJISAE open access articles are licensed under a Creative Commons Attribution-ShareAlike 4.0 International License. This license lets the audience to give appropriate credit, provide a link to the license, and indicate if changes were made and if they remix, transform, or build upon the material, they must distribute contributions under the same license as the original.