First DP procedure for smooth OT map estimation achieving near-minimax optimality in d≥2 and minimax in d=1, with matching lower bounds.
Unsupervised Hyperalignment for Multilingual Word Embeddings
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
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.
years
2026 2verdicts
UNVERDICTED 2representative citing papers
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.
citing papers explorer
-
Minimax Private Estimation of Smooth Optimal-Transport Maps
First DP procedure for smooth OT map estimation achieving near-minimax optimality in d≥2 and minimax in d=1, with matching lower bounds.
-
Spherical Mixture Integration for Latent Embedding Alignment across Multi-Source Feature Spaces
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.