Pith. sign in

REVIEW 3 cited by

Gromov-Wasserstein Alignment of Word Embedding Spaces

Not yet reviewed by Pith; the record is open.

Re-run · record.json Download PDF Read on arXiv ↗

This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.

SPECIMEN: schema-true, not a live event

T0 review · schema-true

One-sentence machine reading of the paper's core claim.

pith:XXXXXXXX · record.json · timestamp

arxiv 1809.00013 v1 pith:QX2I4UXS submitted 2018-08-31 cs.CL

David Alvarez-Melis , Tommi S. Jaakkola This is my paper · ORCID
classification cs.CL
keywords wordalignmentembeddingsgromov-wassersteinmethodsproblemstate-of-the-arttasks
verification ladder T0 review T1 audit T2 compute T3 formal
0 comments
read the original abstract

Cross-lingual or cross-domain correspondences play key roles in tasks ranging from machine translation to transfer learning. Recently, purely unsupervised methods operating on monolingual embeddings have become effective alignment tools. Current state-of-the-art methods, however, involve multiple steps, including heuristic post-hoc refinement strategies. In this paper, we cast the correspondence problem directly as an optimal transport (OT) problem, building on the idea that word embeddings arise from metric recovery algorithms. Indeed, we exploit the Gromov-Wasserstein distance that measures how similarities between pairs of words relate across languages. We show that our OT objective can be estimated efficiently, requires little or no tuning, and results in performance comparable with the state-of-the-art in various unsupervised word translation tasks.

Discussion (0). Continue with ORCID to comment.

Forward citations

Cited by 3 Pith papers

Reviewed papers in the Pith corpus that reference this work. Sorted by Pith novelty score. Full citation record

  1. Robust Alignment via Partial Gromov-Wasserstein Distances

    math.ST 2025-06 conditional novelty 7.0 of 10

    The partial Gromov-Wasserstein distance is shown to be a minimax-optimal estimator of the classical Gromov-Wasserstein distance under total variation contamination.

  2. Neural Estimation for Scaling Entropic Multimarginal Optimal Transport

    cs.LG 2025-05 conditional novelty 7.0 of 10

    NEMOT uses neural dual potentials trained on mini-batches to estimate entropic multimarginal optimal transport costs and plans, with non-asymptotic error guarantees and orders-of-magnitude speedups over Sinkhorn.

  3. Cluster-Aware Matching via Laplacian Optimal Transport

    stat.ML 2026-07 conditional novelty 5.0 of 10

    A Laplacian-regularized optimal transport coupling, plus a post-processing 'Refined Simultaneous Clustering' step, produces cluster-aware alignments and consistent partitions across two point clouds.

Pith tools