Re-evaluating Word Mover's Distance. (arXiv:2105.14403v3 [cs.LG] UPDATED)

Web: http://arxiv.org/abs/2105.14403

The word mover's distance (WMD) is a fundamental technique for measuring the
similarity of two documents. As the crux of WMD, it can take advantage of the
underlying geometry of the word space by employing an optimal transport
formulation. The original study on WMD reported that WMD outperforms classical
baselines such as bag-of-words (BOW) and TF-IDF by significant margins in
various datasets. In this paper, we point out that the evaluation in the
original study could be misleading. We re-evaluate …

arxiv lg