Nepali POS Tagging Using Deep Learning Approaches

Sarbin Sayami, Subarna Shakya


Deep Learning approaches are being extensively used in Part of Speech (POS) tagging. POS tagging is one of the important step in Natural Language Processing (NLP) including Machine Translation, Retrieval of Information, developing question answering system, word sense disambiguation, text summarization, Named Entity Recognition, text to speech conversion and classification. The efficiency of POS tagging heavily rely on syntactic, contextual information and morphology of the language. POS tagging in Nepali Language is very difficult as it is morphologically rich. This research paper focuses on implementing and comparing various deep learning approaches for POS tagging in Nepali Language. Recurrent Neural Network (RNN), Gated Recurrent Unit (GRU), Long Short Term Memory (LSTM) and Bidirectional LSTM were implemented in tagged Nepali corpus. The result of Bidirectional LSTM (Bi-LSTM) was better than other approaches.

Keywords: POS, NLP, RNN, GRU, LSTM, Bi-LSTM, Nepali corpus

Full Text:



Ahmad, A.Z., Rudy, H. and Mustika, I.W. (2017). A Comparison of Different Part-of-Speech Tagging Technique for Text in Bahasa Indonesia .7th International Annual Engineering Seminar (InAES), Yogyakarta, Indonesia.

Rana, F., Mehrnoush, S. and Pouyan, M. (2010). An Efficient Meta Heuristic Algorithm for POS-Tagging. International Conference on Computing in the Global Information Technology (ICCGI), IEEE.

Perez-Ortiz, J.A. and Forcada, M.L. (2001). Part-of-speech tagging with recurrent neural networks. International Joint Conference on Neural Networks Proceedings, IEEE.

Antony, P.J. and Soman, K.P. (2010). Kernel Based Part Of Speech Tagger For Kannada. International Conference on Machine Learning and Cybernetics, IEEE.

Fahim, H.M. (2006). Comparison Of Different Pos Tagging Techniques For Some South Asian Languages. A Thesis Submitted to the Department of Computer Science and Engineering of BRAC University.

Yuan, T. and David, L. (2015). A Comparative Study on the Effectiveness of Part-of-Speech Tagging Techniques on Bug Reports. SANER 2015, Montréal, Canada, IEEE.

Firoj, A. and Shammur, A.C. (2016). Bidirectional LSTMs - CRFs Networks for Bangla POS Tagging. 19th International Conference on Computer and Information Technology, North South University, Dhaka, Bangladesh, IEEE.

Archit, Y. (2018). ANN Based POS Tagging For Nepali Text. International Journal on Natural Language Computing (IJNLC) Vol.7, No.3.

Wang, T.L., Tiago, L., Marujo, L., Ram´on, A.F., Silvio, A., Chris, D., Alan, B. and Isabel, T. (2015). Finding Function in Form: Compositional Character Models for Open Vocabulary Word Representation. Proceedings of the 2015 Conference on Empirical Methods in Natural Language Processing, pages 1520–1530,Lisbon, Portugal, 17-21 September 2015. c 2015 Association for Computational Linguistics, ACL.

Peilu, W., Yao, Q., Frank, S.K., Lei, H. and Hai, Z. (2015). Part-of-Speech Tagging with Bidirectional Long Short-Term Memory Recurrent Neural Network. arXiv:1510.06168v1 [cs.CL].

Yushi, Y. and Zheng, H. (2016). Bi-directional LSTM Recurrent Neural Network for Chinese Word Segmentation. Neural Information Processing: 23rd International Conference, ICONIP 2016, Kyoto, Japan, October 16–21, 2016, Proceedings, Part IV (pp.345- 353).

Greeshma, P., Jyothsna, P.V., Shahina, K.K., Premjith, B. and Soman, K.P. (2018). A Deep Learning Approach for Part-of-Speech Tagging in Nepali Language. International Conference on Advances in Computing, Communications and Informatics, IEEE.


  • There are currently no refbacks.