@InProceedings{drozd-gladkova-matsuoka:2016:COLING,
  author    = {Drozd, Aleksandr  and  Gladkova, Anna  and  Matsuoka, Satoshi},
  title     = {Word Embeddings, Analogies, and Machine Learning: Beyond king - man + woman = queen},
  booktitle = {Proceedings of COLING 2016, the 26th International Conference on Computational Linguistics: Technical Papers},
  month     = {December},
  year      = {2016},
  address   = {Osaka, Japan},
  publisher = {The COLING 2016 Organizing Committee},
  pages     = {3519--3530},
  abstract  = {Solving word analogies became one of the most popular benchmarks for word
	embeddings on the assumption that linear relations between word pairs (such as
	$king$:$man$~:: $woman$:$queen$) are indicative of the quality of the
	embedding. We question this assumption by showing that the information not
	detected by linear offset may still be recoverable by a more sophisticated
	search method, and thus is actually encoded in the embedding.
	The general problem with linear offset is its sensitivity to the idiosyncrasies
	of individual words. We show that simple averaging over multiple word pairs
	improves over the state-of-the-art. A further improvement in accuracy (up to
	{30\%} for some embeddings and relations) is achieved by combining cosine
	similarity with an estimation of the extent to which a candidate answer belongs
	to the correct word class. In addition to this practical contribution, this
	work highlights the problem of the interaction between word embeddings and
	analogy retrieval algorithms, and its implications for the evaluation of word
	embeddings and the use of analogies in extrinsic tasks.},
  url       = {http://aclweb.org/anthology/C16-1332}
}