Advertisement

A Novel Hybridized Strategy for Machine Translation of Indian Languages

  • A. Santhanavijayan
  • D. Naresh Kumar
  • Gerard Deepak
Conference paper
  • 17 Downloads
Part of the Advances in Intelligent Systems and Computing book series (AISC, volume 1118)

Abstract

Only a few translation systems exist for translations between an Aryan language and a Dravidian language, and moreover, the existing system does not perform quite efficiently. In this paper, the cognitive gap between two Indian languages namely Hindi and Malayalam is bridged. This paper proposes a Hindi to Malayalam machine translation system using hybridized strategies such as phrase-based translation, word alignment, and a language model with the emphasis on transition probability computation. Phrase-based translation breaks down a sentence into phrases and translates each phrase independently. This technique is applied on a Hindi–Malayalam parallel corpus. The proposed model interoperates between Hindi and Malayalam Languages. Although standard natural language computing techniques are encompassed, the arrangement of the techniques to suit a pair of Indian languages that are semantically incompliant and achieving a high accuracy is definitely a challenge and is achieved in this paper. The proposed hybridized approach outperforms all the other existing strategies and yields an average precision of 90.725% with a low word error rate of 9.125.

Keywords

Language model Machine translation Phrase-based translation Word alignment 

References

  1. 1.
    Das, A.K., Pradhan, M., Dash, A.K., Pradhan, C., Das, H.: A constructive machine translation system for English to Odia translation. In: 2018 International Conference on Communication and Signal Processing (ICCSP), IEEE, pp. 0854–0857 (2018)Google Scholar
  2. 2.
    Sindhu, D.V., Sagar, B.M.: Study on machine translation approaches for Indian languages and their challenges. In: 2016 International Conference on Electrical, Electronics, Communication, Computer and Optimization Techniques (ICEECCOT), IEEE, pp. 262–267Google Scholar
  3. 3.
    Tennage, P., Sandaruwan, P., Thilakarathne, M., Herath, A., Ranathunga, S., Jayasena, S., Dias, G.: Neural machine translation for Sinhala and Tamil languages. In: 2017 International Conference on Asian Language Processing (IALP), IEEE, pp. 189–192 (2017)Google Scholar
  4. 4.
    Ahmed, R., Al Hasan, M., Selim, R.S.: Aligning sentences in English-Bengali Corpora.” In: 2018 International Conference on Computer, Communication, Chemical, Material and Electronic Engineering (IC4ME2), IEEE, pp. 1–5 (2018)Google Scholar
  5. 5.
    Tholpadi, G., Bhattacharyya, C., Shevade, S.: Corpus-based translation induction in indian languages using auxiliary language corpora from Wikipedia. ACM Trans. Asian Low-Resource Language Inform. Process. 16(3), 20 (2017)Google Scholar
  6. 6.
    Jadoon, N.K., Anwar, W., Bajwa, U.I., Ahmad, F.: Statistical machine translation of Indian languages: a survey. Neural Comput. Appl. 1–13 (2017)Google Scholar
  7. 7.
    Dhariya, O., Malviya, S., Tiwary, U.S.: A hybrid approach for Hindi-English machine translation. In: 2017 International Conference on Information Networking (ICOIN), pp. 389–394. IEEE (2017)Google Scholar
  8. 8.
    Kumar, A., Bansal, N.: Machine translation survey for Punjabi and Urdu languages. In: 2017 3rd International Conference on Advances in Computing, Communication & Automation (ICACCA)(Fall), IEEE, pp. 1–11 (2017)Google Scholar
  9. 9.
    Archana, G.P., Jithesh, V.S., Remya, L.B., Elizabeth, S.: Building a parallel corpora: translation issues and remedial case. In: 2015 International Conference on Advances in Computing, Communications, and Informatics (ICACCI), IEEE, pp. 2414–2417 (2015)Google Scholar
  10. 10.
    Deepak, G., Priyadarshini, J.S., Babu, M.H.: A differential semantic algorithm for query relevant web page recommendation. In: 2016 IEEE International Conference on Advances in Computer Applications (ICACA), IEEE, pp. 44–49Google Scholar
  11. 11.
    Pushpa, C.N., Deepak, G., Thriveni, J., Venugopal, K.R.: Onto collab: strategic review oriented collaborative knowledge modeling using ontologies. In: 2015 Seventh International Conference on Advanced Computing (ICoAC), IEEE, pp. 1–7 (2015)Google Scholar
  12. 12.
    Deepak, G., Ansaf, A., Skanda, B.: An intelligent inventive system for personalized webpage recommendation based on ontology semantics. Int. J. Intell. Syst. Technol. Appl. 18(1/2), 115–132 (2019)Google Scholar
  13. 13.
    Deepak, G., Priyadarshini, S.: A hybrid framework for social tag recommendation using context driven social information. Int. J. Soc. Comput. Cyber-Phys. Syst. 1(4), 312–325 (2016)CrossRefGoogle Scholar
  14. 14.
    Deepak, G., Shwetha, B.N., Pushpa, C.N., Thriveni, J., Venugopal, K.R.: A hybridized semantic trust-based framework for personalized web page recommendation. Int. J. Comput. Appl. 1–11 (2018)Google Scholar
  15. 15.
    Pushpa, C.N., Deepak, G., Thriveni, J. and Venugopal, K.R.: A hybridized framework for ontology modeling incorporating latent semantic analysis and content based filtering. Int. J. Comput. Appl. 150(11) (2016)Google Scholar
  16. 16.
    Deepak, G., Priyadarshini, J.S.: A hybrid semantic algorithm for web image retrieval incorporating ontology classification and user-driven query expansion. Adv. Big Data Cloud Comput. 41 (2018)Google Scholar
  17. 17.
    Gulzar, Z., Leema, A.A., Deepak, G.: PCRS: personalized course recommender system based on hybrid approach. Procedia Comput. Sci. 125, 518–524 (2018)CrossRefGoogle Scholar
  18. 18.
    Deepak, G., Priyadarshini, S.J.: Onto tagger: ontology focused image tagging system incorporating semantic deviation computing and strategic set expansion. Int. J. Comput. Sci. Bus. Inform. 16(1) (2016)Google Scholar
  19. 19.
    Pushpa, C.N., Deepak, G., Zakir, M., Venugopal, K.R.: Enhanced neighborhood normalized pointwise mutual information algorithm for constraint aware data clustering. ICTACT J Soft Comput. 6(4) (2016)Google Scholar
  20. 20.
    Gerard, D., Gulzar, Z.: Ontoepds: Enhanced and personalized differential semantic algorithm incorporating ontology-driven query enrichment. J. Adv. Res. Dyn. Control Syst. 9(no. Special), 567–582 (2017)Google Scholar
  21. 21.
    Giri, G.L., Deepak, G., Manjula, S.H., Venugopal, K.R.: OntoYield: a semantic approach for context-based ontology recommendation based on structure preservation. In: Proceedings of International Conference on Computational Intelligence and Data Engineering, pp. 265–275, Springer, Singapore (2018)Google Scholar
  22. 22.
    Deepak, G., Priyadarshini, J.S.: Personalized and enhanced hybridized semantic algorithm for web image retrieval incorporating ontology classification, strategic query expansion, and content-based analysis. Comput. Electr. Eng. 72, 14–25 (2018)CrossRefGoogle Scholar
  23. 23.
    Santhanavijayan, A., Balasundaram S.R.: Multi swarm optimization based automatic ontology for E-assessment. Comput. Netw. (2019)Google Scholar
  24. 24.
    Manjula, S.H., Venugopal K.R., Patnaik L.M.: Mathematical model of semantic look-an efficient context driven search engine. arXiv preprint. arXiv:1402.7200 (2014)

Copyright information

© Springer Nature Singapore Pte Ltd. 2020

Authors and Affiliations

  • A. Santhanavijayan
    • 1
  • D. Naresh Kumar
    • 2
  • Gerard Deepak
    • 1
  1. 1.Department of Computer Science & EngineeringNational Institute of TechnologyTiruchirappalliIndia
  2. 2.Department of Mechanical EngineeringNational Institute of TechnologyTiruchirappalliIndia

Personalised recommendations