Word2vec Word Similarities on IBM's TrueNorth Neurosynaptic System

Word2vec, like other ways of creating word embeddings from a text corpus, has shown that interesting mathematical properties exist between the resulting word vectors. Word similarities as well as relationships can be discovered by determining which words are nearby in vector space and performing simple vector operations. In this work, IBM's TrueNorth Neurosynaptic System was used to implement massively-parallel word similarity computations using a large network of hardware spiking neurons. A 4-bit vector-matrix multiplication engine was implemented on TrueNorth in order to accommodate a word vector dictionary of 95,000 words trained on Wikipedia text, and it successfully performs word similarity searches using that dictionary while utilizing 3,991 cores out of the 4,096 available on TrueNorth and consuming less than 70 mW of power.