@InProceedings{bhattacharya-goyal-sarkar:2016:WSSANLP2016,
  author    = {Bhattacharya, Paheli  and  Goyal, Pawan  and  Sarkar, Sudeshna},
  title     = {Query Translation for Cross-Language Information Retrieval using Multilingual Word Clusters},
  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     = {152--162},
  abstract  = {In Cross-Language Information Retrieval, finding the appropriate translation of
	the source language query has always been a difficult problem to solve. We
	propose a technique towards solving this problem with the help of multilingual
	word clusters obtained from multilingual word embeddings. We use word
	embeddings of the languages projected to a common vector space on which a
	community-detection algorithm is applied to find clusters such that words that
	represent
	the same concept from different languages fall in the same group. We utilize
	these multilingual word clusters to perform query translation for
	Cross-Language Information Retrieval for three languages - English, Hindi and
	Bengali. We have experimented with the FIRE 2012 and Wikipedia datasets and
	have shown improvements over several standard methods like dictionary-based
	method, a transliteration-based model and Google Translate.},
  url       = {http://aclweb.org/anthology/W16-3716}
}