Skip to yearly menu bar Skip to main content


On the Dimensionality of Word Embedding

Zi Yin · Yuanyuan Shen

Room 517 AB #101

Keywords: [ Natural Language Processing ] [ Embedding Approaches ] [ Matrix and Tensor Factorization ]


In this paper, we provide a theoretical understanding of word embedding and its dimensionality. Motivated by the unitary-invariance of word embedding, we propose the Pairwise Inner Product (PIP) loss, a novel metric on the dissimilarity between word embeddings. Using techniques from matrix perturbation theory, we reveal a fundamental bias-variance trade-off in dimensionality selection for word embeddings. This bias-variance trade-off sheds light on many empirical observations which were previously unexplained, for example the existence of an optimal dimensionality. Moreover, new insights and discoveries, like when and how word embeddings are robust to over-fitting, are revealed. By optimizing over the bias-variance trade-off of the PIP loss, we can explicitly answer the open question of dimensionality selection for word embedding.

Live content is unavailable. Log in and register to view live content