@InProceedings{abdalla-hirst:2017:I17-1,
  author    = {Abdalla, Mohamed  and  Hirst, Graeme},
  title     = {Cross-Lingual Sentiment Analysis Without (Good) Translation},
  booktitle = {Proceedings of the Eighth International Joint Conference on Natural Language Processing (Volume 1: Long Papers)},
  month     = {November},
  year      = {2017},
  address   = {Taipei, Taiwan},
  publisher = {Asian Federation of Natural Language Processing},
  pages     = {506--515},
  abstract  = {Current approaches to cross-lingual sentiment analysis try to leverage the
	wealth of labeled English data using bilingual lexicons, bilingual vector space
	embeddings, or machine translation systems. Here we show that it is possible to
	use a single linear transformation, with as few as 2000 word pairs, to capture
	fine-grained sentiment relationships between words in a cross-lingual setting.
	We apply these cross-lingual sentiment models to a diverse set of tasks to
	demonstrate their functionality in a non-English context. By effectively
	leveraging English sentiment knowledge without the need for accurate
	translation, we can analyze and extract features from other languages with
	scarce data at a very low cost, thus making sentiment and related analyses for
	many languages inexpensive.},
  url       = {http://www.aclweb.org/anthology/I17-1051}
}