Distributed Representations of Words and Phrases and their Compositionality

Title: Distributed Representations of Words and Phrases and their Compositionality
Authors: Tomas Mikolov, Ilya Sutskever, Kai Chen, Greg Corrado, Jeffrey Dean
Published: 16th October 2013 (Wednesday) @ 23:28:53
Link: http://arxiv.org/abs/1310.4546v1

Abstract

The recently introduced continuous Skip-gram model is an efficient method for learning high-quality distributed vector representations that capture a large number of precise syntactic and semantic word relationships. In this paper we present several extensions that improve both the quality of the vectors and the training speed. By subsampling of the frequent words we obtain significant speedup and also learn more regular word representations. We also describe a simple alternative to the hierarchical softmax called negative sampling. An inherent limitation of word representations is their indifference to word order and their inability to represent idiomatic phrases. For example, the meanings of “Canada” and “Air” cannot be easily combined to obtain “Air Canada”. Motivated by this example, we present a simple method for finding phrases in text, and show that learning good vector representations for millions of phrases is possible.

---

Introduce Negative Sampling and subsampling algorithms to improve word vector training efficiency. See eq. 4 for NEG objective function and eq. 5 for subsampling strategy (heuristically chosen).

See also: Efficient Estimation of Word Representations in Vector Space

---