AIRCC's International Journal of Computer Science and Information Technology

Kishorjit Nongmeikapam ¹, R. K. Vidya Raj ², Oinam Imocha Singh ², Sivaji Bandyopadhyay ³

Affiliations
1 Department of Computer Science and Engineering, Manipur Institute of Technology, Manipur University, Imphal, IN
2 Department of Computer Science, Manipur University, Imphal, IN
3 Department of Computer Science and Engineering, Jadavpur Univeristy, Jadavpur, Kolkata, IN

Abstract

The work of automatic segmentation of a Manipuri language (or Meiteilon) word into syllabic units is demonstrated in this paper. This language is a scheduled Indian language of Tibeto-Burman origin, which is also a very highly agglutinative language. This language usage two script: a Bengali script and Meitei Mayek (Script). The present work is based on the second script. An algorithm is design so as to identify mainly the Manipuri origin word. The result of the algorithm shows a Recall is 74.77, Precision is 91.21 and F-Score is 82.18 which is a reasonable score with the first attempt of such kind for this language.

Keywords

Syllable, Syllabic Unit, Manipuri, Meitei Mayek.

Full Text

   

Kishorjit Nongmeikapam ¹, Sivaji Bandyopadhyay ²

Affiliations
1 Department of Computer Sc. and Engineering, Manipur Institute of Technology, Manipur University, Imphal, IN
2 Department of Computer Sc. and Engg., Jadavpur University, Jadavpur, Kolkata, IN

Abstract

This paper deals with the identification of Multiword Expressions (MWEs) in Manipuri, a highly agglutinative Indian Language. Manipuri is listed in the Eight Schedule of Indian Constitution. MWE plays an important role in the applications of Natural Language Processing(NLP) like Machine Translation, Part of Speech tagging, Information Retrieval, Question Answering etc. Feature selection is an important factor in the recognition of Manipuri MWEs using Conditional Random Field (CRF). The disadvantage of manual selection and choosing of the appropriate features for running CRF motivates us to think of Genetic Algorithm (GA). Using GA we are able to find the optimal features to run the CRF. We have tried with fifty generations in feature selection along with three fold cross validation as fitness function. This model demonstrated the Recall (R) of 64.08%, Precision (P) of 86.84% and F-measure (F) of 73.74%, showing an improvement over the CRF based Manipuri MWE identification without GA application.

Keywords

CRF, MWE, Manipuri, GA, Features.

Full Text