@InProceedings{krishna-EtAl:2016:WSSANLP2016,
  author    = {Krishna, Amrith  and  Satuluri, Pavankumar  and  Sharma, Shubham  and  Kumar, Apurv  and  Goyal, Pawan},
  title     = {Compound Type Identification in Sanskrit: What Roles do the Corpus and Grammar Play?},
  booktitle = {Proceedings of the 6th Workshop on South and Southeast Asian Natural Language Processing (WSSANLP2016)},
  month     = {December},
  year      = {2016},
  address   = {Osaka, Japan},
  publisher = {The COLING 2016 Organizing Committee},
  pages     = {1--10},
  abstract  = {classes namely, {\sl Avyay{\=\i}bh{\=a}va}, {\sl Tatpuru\d{s}a}, {\sl
	Bahuvr{\=\i}hi} and {\sl Dvandva}. Our classification is based on the
	traditional classification system followed by the ancient grammar treatise {\sl
	A\d{s}\d{t}{\=a}dhy{\=a}y{\=\i}}, proposed by P{\=a}\d{n}ini 25 centuries back.
	We construct an elaborate features space for our system by combining
	conditional rules from the grammar \Ast, semantic relations between the
	compound components from a lexical database Amarako\d{s}a and linguistic
	structures from the data using Adaptor Grammars. Our in-depth analysis of the
	feature space highlight inadequacy of \Ast, a generative grammar, in
	classifying the data samples. Our experimental results validate the
	effectiveness of using lexical databases as suggested by Amba Kulkarni and Anil
	Kumar, and put forward a new research direction by introducing linguistic
	patterns obtained from Adaptor grammars for effective identification of
	compound type. We utilise an ensemble based approach, specifically designed for
	handling skewed datasets and we  %and Experimenting with various classification
	methods, we
	  achieve an overall accuracy of 0.77 using random forest classifiers.},
  url       = {http://aclweb.org/anthology/W16-3701}
}