From Word Embeddings To Document Distances

Abstract

We present the Word Mover’s Distance (WMD), a novel distance function between text documents. Our work is based on recent results in word embeddings that learn semantically meaningful representations for words from local cooccurrences in sentences. The WMD distance measures the dissimilarity between two text documents as the minimum amount of distance that the embedded words of one document need to “travel” to reach the embedded words of another document. We show that this distance metric can be cast as an instance of the Earth Mover’s Distance, a well studied transportation problem for which several highly efficient solvers have been developed. Our metric has no hyperparameters and is straight-forward to implement. Further, we demonstrate on eight real world document classification data sets, in comparison with seven stateof-the-art baselines, that the WMD metric leads to unprecedented low k-nearest neighbor document classification error rates.

Extracted Key Phrases

8 Figures and Tables

050201520162017
Citations per Year

133 Citations

Semantic Scholar estimates that this publication has 133 citations based on the available data.

See our FAQ for additional information.

Cite this paper

@inproceedings{Kusner2015FromWE, title={From Word Embeddings To Document Distances}, author={Matt J. Kusner and Yu Sun and Nicholas I. Kolkin and Kilian Q. Weinberger}, booktitle={ICML}, year={2015} }