@InProceedings{ponti-vulic-korhonen:2017:starSEM,
  author    = {Ponti, Edoardo Maria  and  Vuli\'{c}, Ivan  and  Korhonen, Anna},
  title     = {Decoding Sentiment from Distributed Representations of Sentences},
  booktitle = {Proceedings of the 6th Joint Conference on Lexical and Computational Semantics (*SEM 2017)},
  month     = {August},
  year      = {2017},
  address   = {Vancouver, Canada},
  publisher = {Association for Computational Linguistics},
  pages     = {22--32},
  abstract  = {Distributed representations of sentences have been developed recently to
	represent their meaning as real-valued vectors. However, it is not clear how
	much information such representations retain about the polarity of sentences.
	To study this question, we decode sentiment from unsupervised sentence
	representations learned with different architectures (sensitive to the order of
	words, the order of sentences, or none) in 9 typologically diverse languages.
	Sentiment results from the (recursive) composition of lexical items and
	grammatical strategies such as negation and concession. The results are
	manifold: we show that there is no `one-size-fits-all' representation
	architecture outperforming the others across the board. Rather, the top-ranking
	architectures depend on the language at hand. Moreover, we find that in several
	cases the additive composition model based on skip-gram word vectors may
	surpass supervised state-of-art architectures such as bi-directional LSTMs.
	Finally, we provide a possible explanation of the observed variation based on
	the type of negative constructions in each language.},
  url       = {http://www.aclweb.org/anthology/S17-1003}
}