mlsanityData to 7 Oct 2026

Re-evaluating Word Mover's Distance

arXiv 2105.14403 ↗First posted 30 May 2021cs.LG cs.CL cs.IRcited by 10

Not on the map. Why?

Abstract (arXiv)

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.

Key facts. Cited by 10 papers in the map (data through 7 Oct 2026). Builds on 51 of its 100 references that are in the map. First posted on arXiv 30 May 2021.

Builds on

51 of 100 references.

References · 51

  1. 2018BERT: Pre-training of Deep Bidirectional Transformers for Language Understandingcited by 40,204
  2. 2019BERTScore: Evaluating Text Generation with BERTcited by 5,462
  3. 2020Dense Passage Retrieval for Open-Domain Question Answeringcited by 3,779
  4. 2013Sinkhorn Distances: Lightspeed Computation of Optimal Transportation Distancescited by 2,277
  5. 2020ColBERT: Efficient and Effective Passage Search via Contextualized Late Interaction over BERTcited by 1,160
  6. 2019MoverScore: Text Generation Evaluating with Contextualized Embeddings and Earth Mover Distancecited by 415
  7. 2020RocketQA: An Optimized Training Approach to Dense Passage Retrieval for Open-Domain Question Answeringcited by 410
  8. 2017Learning Generative Models with Sinkhorn Divergencescited by 310
  9. 2019A Fair Comparison of Graph Neural Networks for Graph Classificationcited by 244
  10. 2019Generalized Sliced Wasserstein Distancescited by 205
  11. 2016Stochastic Optimization for Large-scale Optimal Transportcited by 188
  12. 2021Word Alignment by Fine-tuning Embeddings on Parallel Corporacited by 186
38 more
  1. 2019Are We Really Making Much Progress? A Worrying Analysis of Recent Neural Recommendation Approachescited by 181
  2. 2018Improving GANs Using Optimal Transportcited by 122
  3. 2018Unsupervised Alignment of Embeddings with Wasserstein Procrustescited by 96
  4. 2019Subspace Robust Wasserstein Distancescited by 89
  5. 2020SUPERT: Towards New Frontiers in Unsupervised Evaluation Metrics for Multi-Document Summarizationcited by 69
  6. 2015Sliced Wasserstein Kernels for Probability Distributionscited by 64
  7. 2019Reinforcement Learning Based Graph-to-Sequence Model for Natural Question Generationcited by 57
  8. 2019Tree-Sliced Variants of Wasserstein Distancescited by 54
  9. 2018Baseline Needs More Love: On Simple Word-Embedding-Based Models and Associated Pooling Mechanismscited by 53
  10. 2019Hierarchical Optimal Transport for Document Representationcited by 53
  11. 2016Re-evaluating Automatic Metrics for Image Captioningcited by 45
  12. 2020Projection Robust Wasserstein Distance and Riemannian Optimizationcited by 45
  13. 2020On the Limitations of Cross-lingual Encoders as Exposed by Reference-Free Machine Translation Evaluationcited by 36
  14. 2018Discrete Adversarial Attacks and Submodular Optimization with Applications to Text Classificationcited by 34
  15. 2019Improving Sequence-to-Sequence Learning via Optimal Transportcited by 33
  16. 2020Word Rotator's Distancecited by 32
  17. 2017Structured Optimal Transportcited by 30
  18. 2020A Riemannian Block Coordinate Descent Method for Computing the Projection Robust Wasserstein Distancecited by 27
  19. 2018Word Mover's Embedding: From Word2Vec to Document Embeddingcited by 26
  20. 2019Scalable Nearest Neighbor Search for Optimal Transportcited by 25
  21. 2019Message Passing Attention Networks for Document Understandingcited by 23
  22. 2019Rep the Set: Neural Networks for Learning Set Representationscited by 22
  23. 2018Generalizing Point Embeddings using the Wasserstein Space of Elliptical Distributionscited by 20
  24. 2018Distilled Wasserstein Learning for Word Embedding and Topic Modelingcited by 18
  25. 2020Fast and Robust Comparison of Probability Measures in Heterogeneous Spacescited by 17
  26. 2020Fast Unbalanced Optimal Transport on a Treecited by 16
  27. 2019Learning Embeddings into Entropic Wasserstein Spacescited by 15
  28. 2018Context Mover's Distance & Barycenters: Optimal Transport of Contexts for Building Representationscited by 11
  29. 2021Supervised Tree-Wasserstein Distancecited by 10
  30. 2020Improving Text Generation with Student-Forcing Optimal Transportcited by 8
  31. 2017Does the Geometry of Word Embeddings Help Document Classification? A Case Study on Persistent Homology Based Representationscited by 6
  32. 2019Speeding up Word Mover's Distance and its variants via properties of distances between embeddingscited by 5
  33. 2020A Study of Performance of Optimal Transportcited by 5
  34. 2018Gaussian Word Embedding with a Wasserstein Distance Losscited by 4
  35. 2020P-SIF: Document Embeddings Using Partition Averagingcited by 4
  36. 2020Feature Robust Optimal Transport for High-dimensional Datacited by 4
  37. 2017Regularising Non-linear Models Using Feature Side-informationcited by 3
  38. 2018CoT: Cooperative Training for Generative Modeling of Discrete Datacited by 3

50 most cited of 51 All 51 (JSON)

Built on by

Cited by year

Citing papers per year: 2022: 5; 2023: 3; 2024: 1; 2025: 1.

10 papers.

  1. 2022WikiWhy: Answering and Explaining Cause-and-Effect Questionscited by 21
  2. 2022Approximating 1-Wasserstein Distance with Treescited by 9
  3. 2023Optimal Transport for Measures with Noisy Tree Metriccited by 7
  4. 2022Word Tour: One-dimensional Word Embeddings via the Traveling Salesman Problemcited by 1
  5. 2022Twin Papers: A Simple Framework of Causal Inference for Citations via Couplingcited by 1
  6. 2023Characterizing and Measuring Linguistic Dataset Driftcited by 1
  7. 2022Moving Other Way: Exploring Word Mover Distance Extensionscited by 0
  8. 2023An Empirical Study of Self-supervised Learning with Wasserstein Distancecited by 0
  9. 2024Advanced Machine Learning Framework for Efficient Plant Disease Predictioncited by 0
  10. 2025Global Ground Metric Learning with Applications to scRNA datacited by 0