papers AI Learner
The Github is limit! Click to go to the new site.

Context Vectors are Reflections of Word Vectors in Half the Dimensions

2019-02-26
Zhenisbek Assylbekov, Rustem Takhanov

Abstract

This paper takes a step towards theoretical analysis of the relationship between word embeddings and context embeddings in models such as word2vec. We start from basic probabilistic assumptions on the nature of word vectors, context vectors, and text generation. These assumptions are well supported either empirically or theoretically by the existing literature. Next, we show that under these assumptions the widely-used word-word PMI matrix is approximately a random symmetric Gaussian ensemble. This, in turn, implies that context vectors are reflections of word vectors in approximately half the dimensions. As a direct application of our result, we suggest a theoretically grounded way of tying weights in the SGNS model.

Abstract (translated by Google)
URL

http://arxiv.org/abs/1902.09859

PDF

http://arxiv.org/pdf/1902.09859


Similar Posts

Comments