Word Embeddings, Analogies, and Machine Learning: Beyond king - man + woman = queen

Solving word analogies became one of the most popular benchmarks for word embeddings on the assumption that linear relations between word pairs (such as \textit{king}:\textit{man} :: \textit{woman}:\textit{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.