@InProceedings{kadupitiya-ranathunga-dias:2016:WSSANLP2016,
  author    = {Kadupitiya, Jcs  and  Ranathunga, Surangika  and  Dias, Gihan},
  title     = {Sinhala Short Sentence Similarity Calculation using Corpus-Based and Knowledge-Based Similarity Measures},
  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     = {44--53},
  abstract  = {Currently, corpus based-similarity, string-based similarity, and
	knowledge-based similarity techniques are used to compare short phrases.
	However, no work has been conducted on the similarity of phrases in Sinhala
	language. In this paper, we present a hybrid methodology to compute the
	similarity between two Sinhala sentences using a Semantic Similarity
	Measurement technique (corpus-based similarity measurement plus knowledge-based
	similarity measurement) that makes use of word order information. Since Sinhala
	WordNet is still under construction, we used lexical resources in performing
	this semantic similarity calculation. Evaluation using 4000 sentence pairs
	yielded an average MSE of 0.145 and a Pearson correla-tion factor of 0.832.},
  url       = {http://aclweb.org/anthology/W16-3705}
}