Pith. sign in

REVIEW 3 cited by

Unsupervised Hyperalignment for Multilingual Word Embeddings

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 1811.01124 v3 pith:DUNQSGAO submitted 2018-11-02 cs.CL cs.LG

Unsupervised Hyperalignment for Multilingual Word Embeddings

Jean Alaux , Edouard Grave , Marco Cuturi , Armand Joulin This is my paper
classification cs.CL cs.LG
keywords languageswordaligningcommonindirectmappingsmultipleproblem
verification ladder T0 review T1 audit T2 compute T3 formal T4 reserved
0 comments
read the original abstract

We consider the problem of aligning continuous word representations, learned in multiple languages, to a common space. It was recently shown that, in the case of two languages, it is possible to learn such a mapping without supervision. This paper extends this line of work to the problem of aligning multiple languages to a common space. A solution is to independently map all languages to a pivot language. Unfortunately, this degrades the quality of indirect word translation. We thus propose a novel formulation that ensures composable mappings, leading to better alignments. We evaluate our method by jointly aligning word vectors in eleven languages, showing consistent improvement with indirect mappings while maintaining competitive performance on direct word translation.

discussion (0)

Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.

Forward citations

Cited by 3 Pith papers

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

  1. Minimax Private Estimation of Smooth Optimal-Transport Maps

    math.ST 2026-06 unverdicted novelty 7.0

    First DP procedure for smooth OT map estimation achieving near-minimax optimality in d≥2 and minimax in d=1, with matching lower bounds.

  2. Spherical Mixture Integration for Latent Embedding Alignment across Multi-Source Feature Spaces

    stat.ME 2026-05 unverdicted novelty 6.0

    SMILE aligns latent embeddings across multi-source EHR feature spaces via spherical mixtures of von Mises-Fisher distributions, provides non-asymptotic error bounds, and enables consistent synonym cluster recovery.

  3. Spherical Mixture Integration for Latent Embedding Alignment across Multi-Source Feature Spaces

    stat.ME 2026-05 unverdicted novelty 6.0

    SMILE models synonymy in multi-EHR codes via spherical mixtures of von Mises-Fisher distributions and develops a composite quasi-likelihood estimator with non-asymptotic error bounds and consistent cluster recovery.