SVM based Manipuri POS tagging using SVM based identified reduplicated MWE (RMWE)

ABSTRACT

The Reduplicated Multiword Expression (RMWE) is identified using Support Vector Machine (SVM) and these identified RMWE is used as a feature for the SVM based POS tagging of Manipuri, which is a very highly agglutinative Indian Schedule Language. A common features approach for both RMWE identification and POS tagging is tried. Identification of RMWE using SVM shows the Recall of 86.11%, Precision of 92.08% and F-measure of 88.99%. The identified RMWE is used as a feature in the SVM based POS tagger which results with the Recall of 71.15%, Precision of 83.15% and F-measure of 76.68%.

References

1. Brill, Eric.: A Simple Rule-based Part of Speech Tagger. In the Proceedings of Third International Conference on Applied Natural Language Processing, ACL, Trento, Italy (1992).
2. Brill, Eric.: Transformation-Based Error-Driven Learning and Natural Language Processing: A Case Study in Part of Speech Tagging, Computational Linguistics, Vol. 21(4), pp543--545, (1995).
3. Ratnaparakhi, A.: A maximum entropy Parts- of- Speech Tagger, In the Proceedings EMNLP 1, ACL, pp133--142(1996).
4. Kupiec, R..: Part-of-speech tagging using a Hidden Markov Model, In Computer Speech and Language, Vol 6, No 3, pp225--242(1992).
5. Lin, Y. C., Chiang, T. H. & Su, K. Y.: Discrimination oriented probabilistic tagging, In the Proceedings of ROCLING V, pp87--96(1992).
6. Chang, C. H.& Chen, C. D.: HMM-based Part-of-Speech Tagging for Chinese Corpora, In the Proceedings of the Workshop on Very Large Corpora, Columbus, Ohio, pp40--47(1993).
7. Lua, K. T.: Part of Speech Tagging of Chinese Sentences Using Genetic Algorithm, In the Proceedings of ICCC96, National University of Singapore, pp45--49 (1996).
8. Ekbal, Asif, Mondal, S & Sivaji Bandyopadhyay: POS Tagging using HMM and Rule-based Chunking, In the Proceedings of SPSAL2007, IJCAI, pp25--28, India (2007).
9. Ekbal, Asif, R. Haque & & Sivaji Bandyopadhyay: Bengali Part of Speech Tagging using Conditional Random Field, In the Proceedings 7th SNLP, Thailand (2007).
10. Ekbal, Asif, Haque, R. & & Sivaji Bandyopadhyay: Maximum Entropy based Bengali Part of Speech Tagging, In A. Gelbukh (Ed.), Advances in Natural Language Processing and Applications, Research in Computing Science (RCS) Journal, Vol.(33), pp67--78 (2008).
11. Smriti Singh, Kuhoo Gupta, Manish Shrivastava, & Pushpak Bhattacharya: Morphological Richness offsets Resource Demand --Experiences in constructing a POS tagger for Hindi, In the Proceedings of COLING- ACL, Sydney, Australia (2006).
12. Antony, P. J.; Mohan, S. P.; Soman, K. P.:SVM Based Part of Speech Tagger for Malayalam, In the Proceedings of International Conference on Recent Trends in Information, Telecommunication and Computing (ITC), pp. 339--341, Kochi, Kerala, India (2010).
13. Ekbal, Asif, Mondal, S & Sivaji Bandyopadhyay: Part of Speech Tagging in Bengali Using SVM, In Proceedings of International Conference on Information Technology(ICIT), pp. 106--111, Bhubaneswar, India (2008)
14. Doren Singh, T. & Sivaji Bandyopadhyay, Morphology Driven Manipuri POS Tagger, In the Proceeding of IJCNLP NLPLPL 2008, pp91--97, IIIT Hyderabad (2008).
15. {Doren Singh, T., Ekbal, A. & Sivaji Bandyopadhyay: Manipuri POS tagging using CRF and SVM: A language independent approach, In the proceeding of 6th International conference on Natural Language Processing (ICON -2008), pp 240--245 Pune, India (2008).
16. Kishorjit, N., & Sivaji Bandyopadhyay, Identification of Reduplicated MWEs in Manipuri: A Rule based Approached. In the Proceeding of 23rd International Conference on the Computer Processing of Oriental Languages (ICCPOL-2010), pp49--54, Redwood City, San Francisco, (2010).
17. Kishorjit, N., Dhiraj, L., Bikramjit Singh, N., Mayekleima Chanu, Ng. & Sivaji Bandyopadhyay: Identification of Reduplicated Multiword Expressions Using CRF, A. Gelbukh (Ed.):CICLing 2011, LNCS vol.6608, Part I, pp41--51, Berlin, Germany: Springer-Verlag (2011).
18. Doren Singh, T. & Sivaji Bandyopadhyay: Web Based Manipuri Corpus for Multiword NER and Reduplicated MWEs Identification using SVM, In the Proceedings of the 1st Workshop on South and Southeast Asian Natural Language Processing (WSSANLP), the 23rd International Conference on Computational Linguistics (COLING), pp35--42, Beijing (2010).
19. Dipankar Das, Santanu Pal, Tapabrata Mondal, Tanmoy C & Sivaji Bandyopadhyay: Automatic Extraction of Complex Predicates in Bengali. In the Workshop on Multiword Expressions: from theory to Applications (MWE 2010), 23rd COLING 2010, pp.36--44, August 28, Beijing, China
20. Tanmoy C, Dipankar Das & Sivaji Bandyopadhyay: Semantic Clustering: an Attempt to Identify Multiword Expressions in Bengali. In the proceedings of the Workshop on Multiword Expressions: from Parsing and Generation to the Real World (MWE 2011), 49th Annual Meeting of ACL-HLT 2011, pp. 8--13, Portland, Oregon, USA
21. Nonigopal Singh, N: A Meitei Grammar of Roots and Affixes, A Thesis, (Unpublished), Manipur University, Imphal (1987)
22. Ch. S. Yashawanta, "Manipuri Grammar," Rajesh Publications, Delhi, 2000, pp.190--204
23. Kishorjit, N., Bishworjit, S., Romina, M., Mayekleima Chanu, Ng. & Sivaji Bandyopadhyay: A Light Weight Manipuri Stemmer, In the Proceedings of National Conference on Indian Language Computing (NCILC), Chochin, India (2011).
24. Vapnik, Vladimir N.:The Nature of Statistical Learning Theory. Springer (1995).
25. Cheng-Lung Huang & Chieh-Jen Wang: A GA-based feature selection and parameters optimization for support vector machines, Expert Systems with Applications 31 (2006), doi:10.1016/j.eswa.2005.09.024, Elsevier Publication, pp. 231--240 (2006)
26. Joachims, T.: Making Large Scale SVM Learning Practical. In B. Scholkopf, C. Burges and A. Smola editions, Advances in Kernel Methods-Support Vector Learning (1999)

Index Terms

• Computing methodologies

  • Artificial intelligence

    • Natural language processing

      • Language resources