The DOI matches its Crossref record; 21 of the 21 references it cites were found in a registry or an index.
Gromov-Wasserstein Alignment of Word Embedding Spaces
Open accessAbstract
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-theart 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.
Overview
The claims and statistics of this paper haven’t been checked yet.
Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.
Integrity signals
Registry
Cites
Statistics
Verification
Claims the paper makes
The claims and statistics of this paper haven’t been checked yet.
Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.
Self-check
Percentages, sums and reported differences re-computed from the paper’s own numbers.
The self-check needs the paper’s full text.
Citations
Cites
Enriching Word Vectors with Subword Information
Bojanowski, P., Grave, E., Joulin, A., & Mikolov, T. (2017) · Transactions of the Association for Computational Linguistics · doi:10.1162/tacl_a_00051 · Cited by 9,645 · cited 4×
“Indeed, as pointed out by Artetxe et al. (2018), the FAST T EXT embed-dings provided in this task are trained on very large and highly comparable—across languages— corpora (Wikipedia), and focuses on closely re-lated pairs of languages.”
BackgroundMethodInfluentialSinkhorn Distances: Lightspeed Computation of Optimal TransportPreprint
Cuturi, M. (2013) · Cited by 2,385
A Generalized Solution of the Orthogonal Procrustes Problem
Schönemann, P. H. (1966) · Psychometrika · doi:10.1007/bf02289451 · Cited by 2,040
Exploiting Similarities among Languages for Machine Translation
Mikolov, T., Le, Q. V., & Sutskever, I. (2013) · arXiv (Cornell University) · doi:10.48550/arxiv.1309.4168 · Cited by 1,346
Zipf’s word frequency law in natural language: A critical review and future directions
Piantadosi, S. T. (2014) · Psychonomic Bulletin & Review · doi:10.3758/s13423-014-0585-6 · Cited by 889
Computational Optimal Transport
Peyré, G., & Cuturi, M. (2019) · now publishers, Inc. eBooks · doi:10.1561/9781680835519 · Cited by 847
Word translation without parallel data
Lample, G., Conneau, A., Ranzato, M., Denoyer, L., & Jeǵou, H. (2018) · International Conference on Learning Representations · Cited by 653
Improving Vector Space Word Representations Using Multilingual Correlation
Faruqui, M., & Dyer, C. (2014) · Proceedings of the 14th Conference of the European Chapter of the Association for Computational Linguistics · doi:10.3115/v1/e14-1049 · Cited by 620
Unsupervised Machine Translation Using Monolingual Corpora Only
Lample, G., Conneau, A., Denoyer, L., & Ranzato, M. (2017) · arXiv · doi:10.48550/arxiv.1711.00043 · Cited by 584
A robust self-learning method for fully unsupervised cross-lingual mappings of word embeddings
Artetxe, M., Labaka, G., & Agirre, E. (2018) · Proceedings of the 56th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers) · doi:10.18653/v1/p18-1073 · Cited by 555
A Survey of Cross-lingual Word Embedding Models
Ruder, S., Vulić, I., & Søgaard, A. (2018) · Apollo (University of Cambridge) · doi:10.17863/cam.30462 · Cited by 510
Learning principled bilingual mappings of word embeddings while preserving monolingual invariance
Artetxe, M., Labaka, G., & Agirre, E. (2016) · Proceedings of the 2016 Conference on Empirical Methods in Natural Language Processing · doi:10.18653/v1/d16-1250 · Cited by 369
Improving zero-shot learning by mitigating the hubness problem
Dinu, G., Lazaridou, A., & Baroni, M. (2015) · Figshare · doi:10.5281/zenodo.2654863 · Cited by 310
The softassign Procrustes matching algorithm
Rangarajan, A., Chui, H., & Bookstein, F. L. (1997) · Lecture Notes in Computer Science · doi:10.1007/3-540-63046-5_3 · Cited by 282
Gromov-Wasserstein Averaging of Kernel and Distance Matrices
Gabriel Peyré, A., Cuturi, M., & Solomon, J. (2016) · Base Institutionnelle de Recherche de l'université Paris-Dauphine (BIRD) (University Paris-Dauphine) · Cited by 221
Cross-lingual Dependency Parsing Based on Distributed Representations
Guo, J., Che, W., Yarowsky, D., Wang, H., & Liu, T. (2015) · Proceedings of the 53rd Annual Meeting of the Association for Computational Linguistics and the 7th International Joint Conference on Natural Language Processing (Volume 1: Long Papers) · doi:10.3115/v1/p15-1119 · Cited by 180
Cross-lingual Models of Word Embeddings: An Empirical Comparison
Upadhyay, S., Faruqui, M., Dyer, C., & Roth, D. (2016) · Proceedings of the 54th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers) · doi:10.18653/v1/p16-1157 · Cited by 177
Deep Multilingual Correlation for Improved Word Embeddings
Lu, A., Wang, W., Bansal, M., Gimpel, K., & Livescu, K. (2015) · Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies (NAACL-HLT) · doi:10.3115/v1/n15-1028 · Cited by 134
A survey of cross-lingual embedding models.
Ruder, S. (2017) · Cited by 121
Ten Pairs to Tag – Multilingual POS Tagging via Coarse Mapping between Embeddings
Zhang, Y., Gaddy, D., Barzilay, R., & Jaakkola, T. (2016) · Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies (NAACL-HLT) · doi:10.18653/v1/n16-1156 · Cited by 107
Self-citationWord Embeddings as Metric Recovery in Semantic Spaces
Hashimoto, T., Alvarez-Melis, D., & Jaakkola, T. (2016) · Transactions of the Association for Computational Linguistics · doi:10.1162/tacl_a_00098 · Cited by 103
Self-citation
Cited by
A Survey of Cross-lingual Word Embedding Models
Ruder, S., Vulić, I., & Søgaard, A. (2018) · Apollo (University of Cambridge) · doi:10.17863/cam.30462 · Cited by 510
A Survey of Cross-lingual Word Embedding Models
Ruder, S., Vulić, I., & Søgaard, A. (2019) · Journal of Artificial Intelligence Research · doi:10.1613/jair.1.11640 · Cited by 266
Illuminating protein space with a programmable generative model
Ingraham, J., Baranov, M., Costello, Z., Frappier, V., Ismail, A., Tie, S., Wang, W., Xue, V., Obermeyer, F., Beam, A., et al. (2022) · doi:10.1101/2022.12.01.518682 · Cited by 83
CMOT: cross-modality optimal transport for multimodal inference
Alatkar, S. A., & Wang, D. (2023) · Genome biology · doi:10.1186/s13059-023-02989-8 · Cited by 24
Metadata
- Authors
- Alvarez-Melis, D., & Jaakkola, T.
- Venue
- Proceedings of the 2018 Conference on Empirical Methods in Natural Language Processing
- Published
- 2018
- Pages
- 1881-1890
- OpenAlex
- W2892266277
- Cited by
- 275
- References
- 21
- FWCI
- 16.23
- Type
- conference paper
- Language
- en
- Open access
- hybrid
About these checks
Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.
Statistics and arithmetic are recomputed, not judged.
Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.
What counts as a claim ›How we measure confidence ›How we check this ›
Are you an author, or do you see a problem with this page? Request a review
Data sources
Bibliographic data: Semantic Scholar, OpenAlex, Crossref.
Contains information from the Semantic Scholar Academic Graph Datasets, made available under the ODC Attribution License (ODC-BY 1.0).
Semantic Scholar’s data is described in: Kinney, R., et al. (2023). The Semantic Scholar Open Data Platform. arXiv:2301.10140.