Year: 2018
Type: conference-paper
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-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.
DOI: 10.18653/v1/d18-1214
Authors: David Alvarez-Melis, Tommi Jaakkola
Language: English
Subfield: Artificial Intelligence
Field: Computer Science
Domain: Physical Sciences
Open Access status: hybrid
OpenAlex ID: W2892266277