%0 Conference Proceedings %T Frustratingly Easy Meta-Embedding – Computing Meta-Embeddings by Averaging Source Word Embeddings %A Coates, Joshua %A Bollegala, Danushka %Y Walker, Marilyn %Y Ji, Heng %Y Stent, Amanda %S Proceedings of the 2018 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 2 (Short Papers) %D 2018 %8 June %I Association for Computational Linguistics %C New Orleans, Louisiana %F coates-bollegala-2018-frustratingly %X 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. %R 10.18653/v1/N18-2031 %U https://aclanthology.org/N18-2031 %U https://doi.org/10.18653/v1/N18-2031 %P 194-198