Skip to main content
SpringerLink
Log in

Improving neural machine translation for low-resource Indian languages using rule-based feature extraction

  • Original Article
  • Published:
Neural Computing and Applications Aims and scope Submit manuscript

Abstract

Languages help to unite the world socially, culturally and technologically. Different natives communicate in different languages; there is a tremendous requirement for inter-language information translation process to transfer and share information and ideas. Though Sanskrit is an ancient Indo-European language, a significant amount of work for processing the information is required to explore the full potential of this language to open vistas in computational linguistics and computer science domain. In this paper, we have proposed and presented the machine translation system for translating Sanskrit to the Hindi language. The developed technique uses linguistic features from rule-based feed to train neural machine translation system. The work is novel and applicable to any low-resource language with rich morphology. It is a generic system covering various domains with minimal human intervention. The performance analysis of work is performed on automatic and linguistic measures. The results show that proposed and developed approach outperforms earlier work for this language pair.

This is a preview of subscription content, log in via an institution to check access.

Access this article

Log in via an institution

Price excludes VAT (USA)
Tax calculation will be finalised during checkout.

Instant access to the full article PDF.

Fig. 1
Fig. 2
Fig. 3
Fig. 4
Fig. 5
Fig. 6
Fig. 7
Fig. 8
Fig. 9
Fig. 10

Similar content being viewed by others

References

  1. Forcada ML, Ginestí-Rosell M, Nordfalk J, O’Regan J, Ortiz-Rojas S, Pérez-Ortiz JA, Sánchez-Martínez F, Ramírez-Sánchez G, Tyers FM (2011) Apertium: a free/open-source platform for rule-based machine translation. Mach Transl 25 (2):127–144

    Article  Google Scholar 

  2. Noone G (2003) Machine translation a transfer approach. Computer Science, Linguistics and a Language (CSLL) Department, University of Dublin, Trinity College, Final Rep

  3. Dave S, Parikh J, Bhattacharyya P (2001) Interlingua-based english-hindi machine translation and language divergence. Mach Transl 16 (4):251–304

    Article  Google Scholar 

  4. Brown PF, Pietra VJD, Pietra SAD, Mercer RL (1993) The mathematics of statistical machine translation: parameter estimation. Comput Linguist 19 (2):263–311

    Google Scholar 

  5. Bahdanau D, Cho K, Bengio Y (2014) Neural machine translation by jointly learning to align and translate. arXiv preprint arXiv:14090473

  6. Somers H (1999) Example-based machine translation. Mach Transl 14 (2):113–157

    Article  MathSciNet  Google Scholar 

  7. Nirenburg S et al (1989) kbmt-89 project report. Center for Machine Translation, Carnegie Mellon University, Pittsburg p 286

  8. Pandey R, Ojha AK, Jha GN (2018) Demo of Sanskrit–hindi smt system. arXiv preprint arXiv:180406716

  9. Huet G, Kulkarni A, Scharf P (2009) Sanskrit computational linguistics. Lecture Notes in Computer Science 5402

  10. of India G (2018) Census-2018, language-census of india, states and union territories. www.censusindia.gov.in/2011Census/C-16_25062018_NEW.pdf

  11. Baindur M (2015) Nature in Indian philosophy and cultural traditions. Springer, Berlin

    Book  Google Scholar 

  12. Jha GN, Mishra SK, Chandrashekar R (2005) Developing a sanskrit analysis system for machine translation. In: Proc. National Seminar on Translation Today: state and issues, Dept. of Linguistics, University of Kerala, Trivandrum, pp 23–25

  13. Bharati A, Chaitanya V, Sangal R, Ramakrishnamacharyulu K (1995) Natural language processing: a Paninian perspective. Prentice-Hall of India, New Delhi

    Google Scholar 

  14. Huet G (2009) Formal structure of Sanskrit text: Requirements analysis for a mechanical Sanskrit processor. In: Sanskrit Computational Linguistics, Springer, Berlin, pp 162–199

  15. Bharati A, Chaitanya V, Sangal R (1994) Paninian framework and its application toanusaraka. Sadhana 19 (1):113–127

    Article  Google Scholar 

  16. Bharati A, Kulkarni A (2007) Sanskrit and computational linguistics. In: 1st International Sanskrit Computational Symposium. Department of Sanskrit Studies, University of Hyderabad

  17. Nair RR, Devi LS (2011) Sanskrit Informatics: Informatics for Sanskrit studies and research. Centre for Informatics Research and Development

  18. Shukla P, Shukl D, Kulkarni A (2010) Vibhakti divergence between Sanskrit and Hindi. In: International Sanskrit Computational Linguistics Symposium, Springer, Berlin, pp 198–208

  19. Waibel A, Jain AN, McNair AE, Saito H, Hauptmann AG, Tebelskis J (1991) Janus: a speech-to-speech translation system using connectionist and symbolic processing strategies. In: International conference on acoustics, speech, and signal processing, 1991. ICASSP-91, IEEE, pp 793–796

  20. Castano MA, Casacuberta F, Vidal E (1997) Machine translation using neural networks and finite-state models. Theoretical and Methodological Issues in Machine Translation (TMI), pp 160–167

  21. Forcada ML, \(\tilde{N}\)eco RP (1997) Recursive hetero-associative memories for translation. In: International work-conference on artificial neural networks. Springer, Berlin, pp 453–462

  22. Bengio Y, Ducharme R, Vincent P, Jauvin C (2003) A neural probabilistic language model. J Mach Learn Res 3 (Feb):1137–1155

    MATH  Google Scholar 

  23. Schwenk H (2007) Continuous space language models. Comput Speech Lang 21 (3):492–518

    Article  Google Scholar 

  24. Mikolov T (2012) Statistical language models based on neural networks. Presentation at Google, Mountain View, 2nd April

  25. Devlin J, Zbib R, Huang Z, Lamar T, Schwartz R, Makhoul J (2014) Fast and robust neural network joint models for statistical machine translation. In: Proceedings of the 52nd annual meeting of the association for computational linguistics (vol 1: Long Papers), vol 1, pp 1370–1380

  26. Schwenk H, Rousseau A, Attik M (2012) Large, pruned or continuous space language models on a GPU for statistical machine translation. In: Proceedings of the NAACL-HLT 2012 workshop: will we ever really replace the N-gram model? On the future of language modeling for HLT, Association for Computational Linguistics, pp 11–19

  27. Wu Y, Yamamoto H, Lu X, Matsuda S, Hori C, Kashioka H (2012) Factored recurrent neural network language model in ted lecture transcription. In: International workshop on spoken language translation (IWSLT) 2012

  28. De Gispert A, Iglesias G, Byrne B (2015) Fast and accurate preordering for SMT using neural networks. In: Proceedings of the 2015 conference of the North American chapter of the association for computational linguistics: human language technologies, pp 1012–1017

  29. Kanouchi S, Sudoh K, Komachi M (2016) Neural reordering model considering phrase translation and word alignment for phrase-based translation. In: Proceedings of the 3rd workshop on Asian translation (WAT2016), pp 94–103

  30. Li J, Marton Y, Resnik P, Daumé III H (2014) A unified model for soft linguistic reordering constraints in statistical machine translation. In: Proceedings of the 52nd annual meeting of the association for computational linguistics (vol 1: Long Papers), vol 1, pp 1123–1133

  31. Kalchbrenner N, Blunsom P (2013) Recurrent continuous translation models. In: Proceedings of the 2013 conference on empirical methods in natural language processing, pp 1700–1709

  32. Luong MT, Pham H, Manning CD (2015) Effective approaches to attention-based neural machine translation. arXiv preprint arXiv:150804025

  33. Thieme P (1958) The indo-european language. Sci Am 199 (4):63–78

    Article  Google Scholar 

  34. Indhuja K, Indu M, Sreejith C, Sreekrishnapuram P, Raj PR (2014) Text based language identification system for indian languages following devanagiri script. Int J Eng 3 (4):1

    Google Scholar 

  35. Chandra S (2005) Developing a sanskrit analysis system for machine translation. National seminar on translation today state and issues

  36. Staal JF (1963) Sanskrit and sanskritization. J Asian Stud 22 (3):261–275

    Article  Google Scholar 

  37. Ramanujan P (1992) Computer processing of sanskrit. Computer Processing of Asian Languages CALP-2, IIT Kanpur

  38. Mishra V, Mishra R (2009a) Divergence patterns between english and sanskrit machine translation. INFOCOMP 8 (3):62–71

    Google Scholar 

  39. Mishra V, Mishra R (2009b) Ann and rule based model for english to sanskrit machine translation. INFOCOMP 9 (1):80–89

    Google Scholar 

  40. Mane D, Devale P, Suryawans S (2010) A design towards english to sanskrit machine translation and sy thesizer syste 1 si grule base approach. Int J Multidisp Res Adv Eng 1:1

    Google Scholar 

  41. Barkade V, Devale PR (2010) English to sanskrit machine translation semantic mapper. Int J Eng Sci Technol 2 (10):5313–5318

    Google Scholar 

  42. Shukla P, Shukla A (2014) English speech to sanskrit speech (ESSS) using rule based translation. Int J Comput Appl 92 (10):1

    Google Scholar 

  43. Rathod SG, Sondur S (2012) English to sanskrit translator and synthesizer (ETSTS). Int J Emerg Technol Adv Eng 2 (12):1

    Google Scholar 

  44. Bahadur P, Jain A, Chauhan D (2012) Etrans-a complete framework for english to sanskrit machine translation. In: International Journal of Advanced Computer Science and Applications (IJACSA) from International Conference and workshop on Emerging Trends in Technology, Citeseer

  45. Upadhyay P, Jaiswal UC, Ashish K (2014) Transish: translator from sanskrit to english-a rule based machine translation. Int J Curr Eng Technol E-ISSN 1:2277–4106

    Google Scholar 

  46. Warhade SR, Patil SH, Devale PR (2012) English-to-sanskrit statistical machine translation with ubiquitous application. Int J Comput Appl 51 (1):1

    Google Scholar 

  47. Jha GN (2010) The tdil program and the indian langauge corpora intitiative (ilci). In: LREC

  48. Nair SS, Kulkarni A (2010) The knowledge structure in amarakośa. In: Sanskrit Computational Linguistics, Springer, Berlin, pp 173–189

  49. Kulkarni A (2002) Samsaadhani, a sanskrit computational toolkit. http://scl.samsaadhanii.in/scl/

  50. Kumar A, Mittal V, Kulkarni A (2010) Sanskrit compound processor. In: Sanskrit Computational Linguistics, Springer, Berlin, pp 57–69

  51. Pandey RK, Jha GN (2016) Error analysis of sahit-a statistical sanskrit-hindi translator. Procedia Comput Sci 96:495–501

    Article  Google Scholar 

  52. Chaudhury S, Rao A, Sharma DM (2010) Anusaaraka: An expert system based machine translation system. In: International conference on natural language processing and knowledge engineering (NLP-KE), 2010, IEEE, pp 1–6

  53. Pappu A, Sanyal R (2008) Vaakkriti: Sanskrit tokenizer. In: Proceedings of the 3rd international joint conference on natural language processing: volume-II

  54. Sachin K (2007) Sandhi splitter and analyzer for sanskrit (with reference to ac sandhi). Mphil degree at SCSS, JNU (submitted, 2007)

  55. Kumar S (2007) Sandhi splitter and analyzer for sanskrit. with special reference to aC sandhi

  56. Bharati A, Kulkarni AP, Sheeba V (2006) Building a wide coverage sanskrit morphological analyser: A practical approach. In: The 1st national symposium on modelling and shallow parsing of Indian languages, IIT-Bombay

  57. Mittal V (2010) Automatic sanskrit segmentizer using finite state transducers. In: Proceedings of the ACL 2010 student research workshop, Association for Computational Linguistics, pp 85–90

  58. Jha GN, Agrawal M, Mishra SK, Mani D, Mishra D, Bhadra M, Singh SK, et al (2009) Inflectional morphology analyzer for sanskrit. In: Sanskrit computational linguistics, Springer, pp 219–238

  59. Kulkarni A, Pokar S, Shukl D (2010) Designing a constraint based parser for sanskrit. In: Sanskrit Computational Linguistics, Springer, pp 70–90

  60. Goyal P, Arora V, Behera L (2009) Analysis of sanskrit text: Parsing and semantic relations. In: Sanskrit Computational Linguistics, Springer, pp 200–218

  61. Kulkarni A, Kumar A (2011) Statistical constituency parser for sanskrit compounds. In: Proceedings of ICON

  62. Kulkarni A, Ramakrishnamacharyulu K (2013) Parsing sanskrit texts: Some relation specific issues. In: Proceedings of the 5th international sanskrit computational linguistics symposium. DK Printworld (P) Ltd

  63. Kulkarni A (2013) A deterministic dependency parser with dynamic programming for sanskrit. In: Proceedings of the 2nd international conference on dependency linguistics (DepLing 2013), pp 157–166

  64. Huet G (2006) Shallow syntax analysis in sanskrit guided by semantic nets constraints. In: Proceedings of the 2006 international workshop on Research issues in digital libraries, ACM, p 6

  65. Hellwig O (2009) Sanskrittagger: A stochastic lexical and pos tagger for sanskrit. In: Sanskrit computational linguistics, Springer, pp 266–277

  66. Hellwig O (2010) Performance of a lexical and pos tagger for sanskrit. In: Sanskrit computational linguistics, Springer, pp 162–172

  67. Nandi M, Ramasree R (2013) Rule-based extraction of multi-word expressions for elementary sanskrit texts. Int J 3 (11):1

    Google Scholar 

  68. Kumar A, Sheebasudheer V, Kulkarni A (2009) Sanskrit compound paraphrase generator. In: Proceedings of ICON

  69. Chung J, Gulcehre C, Cho K, Bengio Y (2014) Empirical evaluation of gated recurrent neural networks on sequence modeling. arXiv preprint arXiv:14123555

  70. Sennrich R, Haddow B (2016) Linguistic input features improve neural machine translation. arXiv preprint arXiv:160602892

  71. Li Y, Yuan Y (2017) Convergence analysis of two-layer neural networks with relu activation. In: Advances in neural information processing systems, pp 597–607

  72. Montufar GF, Pascanu R, Cho K, Bengio Y (2014) On the number of linear regions of deep neural networks. In: Advances in neural information processing systems, pp 2924–2932

  73. News S (2018) Sanskrit News, “department of public health relations”. http://mpinfo.org/News/SanskritNews.aspx

  74. Belinkov Y, Bisk Y (2017) Synthetic and natural noise both break neural machine translation. arXiv preprint arXiv:171102173

  75. Computational Linguistics J (2019) Sanskrit corpora. http://sanskrit.jnu.ac.in/corpora/tagset.jsp

  76. Department of Sanskrit Studies UoH (2019) Digital sanskrit corpora. http://sanskrit.uohyd.ac.in/Corpus/

  77. Zeiler MD (2012) Adadelta: an adaptive learning rate method. arXiv preprint arXiv:12125701

  78. Kingma DP, Ba J (2014) Adam: A method for stochastic optimization. arXiv preprint arXiv:14126980

  79. Ioffe S, Szegedy C (2015) Batch normalization: Accelerating deep network training by reducing internal covariate shift. arXiv preprint arXiv:150203167

  80. Papineni K, Roukos S, Ward T, Zhu WJ (2002) Bleu: a method for automatic evaluation of machine translation. In: Proceedings of the 40th annual meeting on association for computational linguistics, Association for Computational Linguistics, pp 311–318

  81. Mikolov T, Karafiát M, Burget L, Černockỳ J, Khudanpur S (2010) Recurrent neural network based language model. In: 11th Annual conference of the international speech communication association

Download references

Author information

Authors and Affiliations

  1. Language Engineering and Machine Learning Research Labs, CSED, Thapar Institute of Engineering and Technology (TIET), Patiala, India

    Muskaan Singh

  2. CSED, Thapar Institute of Engineering and Technology (TIET), Patiala, India

    Ravinder Kumar & Inderveer Chana

Authors
  1. Muskaan Singh
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. Ravinder Kumar
    View author publications

    You can also search for this author in PubMed Google Scholar

  3. Inderveer Chana
    View author publications

    You can also search for this author in PubMed Google Scholar

Corresponding author

Correspondence to Muskaan Singh.

Ethics declarations

Conflict of interest

The authors declare that they have no conflict of interest.

Additional information

Publisher's Note

Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.

Rights and permissions

Reprints and permissions

About this article

Check for updates. Verify currency and authenticity via CrossMark

Cite this article

Singh, M., Kumar, R. & Chana, I. Improving neural machine translation for low-resource Indian languages using rule-based feature extraction. Neural Comput & Applic 33, 1103–1122 (2021). https://doi.org/10.1007/s00521-020-04990-9

Download citation

  • Received:

  • Accepted:

  • Published:

  • Issue Date:

  • DOI: https://doi.org/10.1007/s00521-020-04990-9

Keywords

Search

Navigation