@InProceedings{coates-bollegala:2018:N18-2,
  author    = {Coates, Joshua  and  Bollegala, Danushka},
  title     = {Frustratingly Easy Meta-Embedding -- Computing Meta-Embeddings by Averaging Source Word Embeddings},
  booktitle = {Proceedings of the 2018 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 2 (Short Papers)},
  month     = {June},
  year      = {2018},
  address   = {New Orleans, Louisiana},
  publisher = {Association for Computational Linguistics},
  pages     = {194--198},
  abstract  = {Creating accurate meta-embeddings from pre-trained source embeddings has received attention lately. Methods based on global and locally-linear transformation and concatenation have shown to produce accurate meta-embeddings. In this paper, we show that the arithmetic mean of two distinct word embedding sets yields a performant meta-embedding that is comparable or better than more complex meta-embedding learning methods. The result seems counter-intuitive given that vector spaces in different source embeddings are not comparable and cannot be simply averaged. We give insight into why averaging can still produce accurate meta-embedding despite the incomparability of the source vector spaces.},
  url       = {http://www.aclweb.org/anthology/N18-2031}
}