Dynamic word embeddings for evolving semantic discovery

One of the most popular posts on this blog is my introduction to word embeddings with word2vec ('The amazing power of word vectors'). In today's paper choice Yao et al. introduce a lovely extension that enables you to track how the meaning of words changes over time. It would be a superb tool for analysing brands for example. Human language is an evolving construct, with word semantic associations changing over time. For example, apple which was traditionally only associated with fruits, is now also associated with a technology company.