Distributed Representations of Words and Phrases and their Compositionality

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.

View Slides

Extracted Key Phrases

8 Figures and Tables

010002000201320142015201620172018
Citations per Year

5,760 Citations

Semantic Scholar estimates that this publication has 5,760 citations based on the available data.

See our FAQ for additional information.

Cite this paper

@inproceedings{Mikolov2013DistributedRO, title={Distributed Representations of Words and Phrases and their Compositionality}, author={Tomas Mikolov and Ilya Sutskever and Kai Chen and Gregory S. Corrado and Jeffrey Dean}, booktitle={NIPS}, year={2013} }