@InProceedings{gyanendrosingh-laitonjam-ranbirsingh:2016:COLING,
  author    = {Gyanendro Singh, Loitongbam  and  Laitonjam, Lenin  and  Ranbir Singh, Sanasam},
  title     = {Automatic Syllabification for Manipuri language},
  booktitle = {Proceedings of COLING 2016, the 26th International Conference on Computational Linguistics: Technical Papers},
  month     = {December},
  year      = {2016},
  address   = {Osaka, Japan},
  publisher = {The COLING 2016 Organizing Committee},
  pages     = {349--357},
  abstract  = {Development of hand crafted rule for syllabifying words of a language is an
	expensive task. 
	This paper proposes several data-driven methods for automatic syllabification
	of words written in Manipuri language. Manipuri is one of the scheduled Indian
	languages. First, we propose a language-independent rule-based approach
	formulated using entropy based phonotactic segmentation. Second, we project the
	syllabification problem as a sequence labeling problem and investigate its
	effect using various sequence labeling approaches. Third, we combine the effect
	of sequence labeling and rule-based method and investigate the performance of
	the hybrid approach. 
	From various experimental observations, it is evident that the proposed methods
	outperform the baseline rule-based method. 
	The entropy based phonotactic segmentation provides a word accuracy of 96%, CRF
	(sequence labeling approach) provides 97% and hybrid approach provides 98% word
	accuracy.},
  url       = {http://aclweb.org/anthology/C16-1034}
}

