Re-evaluating Word Mover's Distance

Abstract

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 the performances of WMD and the classical baselines and find that the classical baselines are competitive with WMD if we employ an appropriate preprocessing, i.e., L1 normalization. In addition, we introduce an analogy between WMD and L1-normalized BOW and find that not only the performance of WMD but also the distance values resemble those of BOW in high dimensional spaces.

ICML 2022

References in corpus (8)

• BERTScore: Evaluating Text Generation with BERT
• A Fair Comparison of Graph Neural Networks for Graph Classification
• Hierarchical Optimal Transport for Document Representation
• Rep the Set: Neural Networks for Learning Set Representations
• Fast and Robust Comparison of Probability Measures in Heterogeneous Spaces
• A Study of Performance of Optimal Transport
• Learning Embeddings into Entropic Wasserstein Spaces
• Feature Robust Optimal Transport for High-dimensional Data