Word sense disambiguation for Punjabi language using deep learning techniques

  • Varinder pal SinghEmail author
  • Parteek Kumar
Review Article


Word sense disambiguation (WSD) identifies the right meaning of the word in the given context. It is an indispensable and critical application for all the natural language processing tasks. In this paper, two deep learning techniques multilayer perceptron and long short-term memory (LSTM) have been individually inspected on the word vectors of 66 ambiguous Punjabi nouns for an explicit WSD system of Punjabi language. The inputs to the deep learning techniques are the simple word vectors derived directly from manually sense-tagged corpus of Punjabi language. The multilayer perceptron has outperformed the LSTM deep learning technique for WSD task of Punjabi language. Six traditional supervised machine learning techniques have also been tested on same dataset using unigram and bigram feature sets. A comparison between deep learning techniques and traditional six supervised machine learning techniques clearly indicates that the deep learning techniques using simple word vectors outperforms the earlier techniques.


Word sense disambiguation Machine learning Deep learning 



This Publication is an outcome of the R&D work undertaken in the project under the Visvesvaraya Ph.D. Scheme of Ministry of Electronics and Information Technology, Government of India, being implemented by Digital India Corporation (formerly Media Lab Asia).

Compliance with ethical standards

Conflict of interest

The authors declare that they have no conflict of interest regarding the contents of present article.


  1. 1.
    Navigli R (2009) Word sense disambiguation: a survey. ACM Comput Surv 41:1–69CrossRefGoogle Scholar
  2. 2.
    Vidhu Bhala R, Abirami S (2014) Trends in word sense disambiguation. Artif Intell Rev 42:159–171CrossRefGoogle Scholar
  3. 3.
    Azzini A, Pereira CDC, Dragoni M, Tettamanzi AGB (2008) Evolving neural networks for word sense disambiguation. IEEE Eighth Int Conf Hybrid Intell Syst Barcelona 2008:332–337Google Scholar
  4. 4.
    Manning CD (2016) Computational linguistics and deep learning. Comput Linguist 41(4):701–707MathSciNetCrossRefGoogle Scholar
  5. 5.
    Severyn A, Moschitti A (2015) Twitter sentiment analysis with deep convolutional neural networks. In ACM: Proceedings of the 38th international ACM SIGIR conference on research and development in information retrieval, Santiago, Chile, pp 959–962Google Scholar
  6. 6.
    Deng LAO (2013) Recent advances in deep learning for speech research at Microsoft. In: 2013 IEEE international conference on IEEE acoustics, speech and signal processing (ICASSP), pp 8604–8608Google Scholar
  7. 7.
    Khademian Mahdi, Homayounpour Mohammad Mehdi (2017) Feature joint-state posterior estimation in factorial speech processing models using deep neural networks. Comput Electr Eng 62:574–587CrossRefGoogle Scholar
  8. 8.
    LeCun Y, Bengio Y, Hinton G (2015) Deep learning. Nature 521:436–444CrossRefGoogle Scholar
  9. 9.
    Uddin MZ, Hassan MM, Almogren A, Zuair M, Fortino G, Torresen J (2017) A facial expression recognition system using robust face features from depth videos and deep learning. Comput Electr Eng 63:114–125CrossRefGoogle Scholar
  10. 10.
    Deselaers T, Hasan S, Bender O, Ney H (2009) A deep learning approach to machine transliteration. In Association for computational linguistics: proceedings of the fourth workshop on statistical machine translation, Athens, Greece, pp 233–241Google Scholar
  11. 11.
    Veronis, JI, Nancy M (1990) Word sense disambiguation with very large neural networks extracted from machine readable dictionaries. In: Proceedings of the 13th conference on computational linguistics-volume 2, StockholmGoogle Scholar
  12. 12.
    Mooney R (1996) Comparative experiments on disambiguating word senses: an illustration of the role of bias in machine learning. arXiv preprint cmp-lg/9612001, pp 1–10Google Scholar
  13. 13.
    Zuppann A (2003) A connectionist approach to word sense disambiguation. In: Class of 2003 senior conference on natural language processing, SwarthmoreGoogle Scholar
  14. 14.
    Lu Z, Liu T, Li S (2004) Combining neural networks and statistics for chinese word sense disambiguation. In: Proceedings of the third SIGHAN workshop on Chinese language processing, Barcelona, Spain, pp 49–56Google Scholar
  15. 15.
    Collobert R, Weston J (2008) A unified architecture for natural language processing: deep neural networks with multitask learning. In: Proceedings of the 25th international conference on machine learning, Helsinki, Finland, pp 160–167Google Scholar
  16. 16.
    Young T, Hazarika D, Poria SE (2018) Recent trends in deep learning based natural language processing. IEEE Comput Intell Mag 13(3):55–75CrossRefGoogle Scholar
  17. 17.
    Popov A (2018) Neural network models for word sense disambiguation: an overview. Cybern Inform Technol 18(1):139–151MathSciNetCrossRefGoogle Scholar
  18. 18.
    Wiriyathammabhum P, Kijsirikul B, Takamura H, Okumura M (2012) Applying deep belief networks to word sense disambiguation. arXiv preprint arXiv:1207.0396, pp 1–8
  19. 19.
    S. Gupta, A. Namavari and T. O. Smith (2016) Word sense disambiguation using skip-gram and LSTM models., pp 1–9Google Scholar
  20. 20.
    Kageback M, Salomonsson H (2016) Word sense disambiguation using a bidirectional LSTM. arXiv preprint arXiv:1606.03568, pp 1–6
  21. 21.
    Yuan D, Richardson J, Doherty R, Evans C, Altendorf E (2016) Semi-supervised word sense disambiguation with neural models. arXiv preprint arXiv:1603.07012, pp 1–12
  22. 22.
    Punjabi Language. (n.d.). (Wikipedia) Retrieved 02 07, 2018.
  23. 23.
    Kachru B, Kachru Y, Sridhar S (2008) Language in South Asia. Cambridge University Press, CambridgeCrossRefGoogle Scholar
  24. 24.
    Verma K, Sharma RK (2017) Comparison of HMM- and SVM-based stroke classifiers for Gurmukhi script. Neural Comput Appl 21(1):51–63CrossRefGoogle Scholar
  25. 25.
    Singh H, Sharma RK, Singh VP (2018) Efficient zone identification approach for the recognition of online handwritten Gurmukhi script. Neural Comput Appl. CrossRefGoogle Scholar
  26. 26.
    Khan Jadoon N, Anwar W, Bajwa UI, Ahmad F (2017) Statistical machine translation of Indian languages: a survey. Neural Comput Appl 31:1–13. CrossRefGoogle Scholar
  27. 27.
    Punjabi Shallow Parser (2018) LTRC IIIT Hyderabad. Accessed 7 Feb 2018
  28. 28.
    Josan G, Lehal G (2008) Size of N for word sense disambiguation using N-gram model for punjabi language. Int J Transl 20(1–2):47–56Google Scholar
  29. 29.
    Rana P, Kumar P (2015) Word sense disambiguation for Punjabi language using overlap based approach in advances in intelligent informatics. Springer, Berlin, pp 607–619Google Scholar
  30. 30.
    Singh J, Singh I (2015) Word sense disambiguation: enhanced lesk approach in Punjabi language. Int J Comput Appl 129(6):23–27Google Scholar
  31. 31.
    Singh VP, Kumar P (2018) Naive Bayes classifier for word sense disambiguation of Punjabi language. Malays J Comput Sci 31(3):188–199CrossRefGoogle Scholar
  32. 32.
    Narang A, Sharma R, Kumar P (2013) Development of Punjabi WordNet. CSI Trans ICT 1(4):349–354CrossRefGoogle Scholar
  33. 33.
    Bhattacharya P (2010) IndoWordNet. In: Proceeding of lexical resources engineering Malta, pp 1–8Google Scholar
  34. 34.
    Kumar P, Sharma R, Narang A (2014) Creation of lexical relations for IndoWordNet. In: Proceedings of the seventh global Wordnet conference, pp 206–214Google Scholar
  35. 35.
    Chollet F (2015) Keras, GitHub repositoryGoogle Scholar

Copyright information

© Springer-Verlag London Ltd., part of Springer Nature 2019

Authors and Affiliations

  1. 1.Computer Science and Engineering DepartmentThapar UniversityPatialaIndia

Personalised recommendations