@InProceedings{levy-sogaard-goldberg:2017:EACLlong,
  author    = {Levy, Omer  and  S{\o}gaard, Anders  and  Goldberg, Yoav},
  title     = {A Strong Baseline for Learning Cross-Lingual Word Embeddings from Sentence Alignments},
  booktitle = {Proceedings of the 15th Conference of the European Chapter of the Association for Computational Linguistics: Volume 1, Long Papers},
  month     = {April},
  year      = {2017},
  address   = {Valencia, Spain},
  publisher = {Association for Computational Linguistics},
  pages     = {765--774},
  abstract  = {While cross-lingual word embeddings have been studied extensively in recent
	years, the qualitative differences between the different algorithms remain
	vague. We observe that whether or not an algorithm uses a particular feature
	set (sentence IDs) accounts for a significant performance gap among these
	algorithms. This feature set is also used by traditional alignment algorithms,
	such as IBM Model-1, which demonstrate similar performance to state-of-the-art
	embedding algorithms on a variety of benchmarks. Overall, we observe that
	different algorithmic approaches for utilizing the sentence ID feature space
	result in similar performance. This paper draws both empirical and theoretical
	parallels between the embedding and alignment literature, and suggests that
	adding additional sources of information, which go beyond the traditional
	signal of bilingual sentence-aligned corpora, may substantially improve
	cross-lingual word embeddings, and that future baselines should at least take
	such features into account.},
  url       = {http://www.aclweb.org/anthology/E17-1072}
}