arXiv Analytics

Sign in

arXiv:1911.02536 [cs.LG]AbstractReferencesReviewsResources

Unsupervised Hierarchy Matching with Optimal Transport over Hyperbolic Spaces

David Alvarez-Melis, Youssef Mroueh, Tommi S. Jaakkola

Published 2019-11-06Version 1

This paper focuses on the problem of unsupervised alignment of hierarchical data such as ontologies or lexical databases. This is a problem that appears across areas, from natural language processing to bioinformatics, and is typically solved by appeal to outside knowledge bases and label-textual similarity. In contrast, we approach the problem from a purely geometric perspective: given only a vector-space representation of the items in the two hierarchies, we seek to infer correspondences across them. Our work derives from and interweaves hyperbolic-space representations for hierarchical data, on one hand, and unsupervised word-alignment methods, on the other. We first provide a set of negative results showing how and why Euclidean methods fail in this hyperbolic setting. We then propose a novel approach based on optimal transport over hyperbolic spaces, and show that it outperforms standard embedding alignment techniques in various experiments on cross-lingual WordNet alignment and ontology matching tasks.

Related articles: Most relevant | Search more
arXiv:1912.02160 [cs.LG] (Published 2019-12-04)
Informative GANs via Structured Regularization of Optimal Transport
arXiv:1903.03850 [cs.LG] (Published 2019-03-09)
Stochastic Incremental Algorithms for Optimal Transport with SON Regularizer
arXiv:1905.11885 [cs.LG] (Published 2019-05-28)
Differentiable Sorting using Optimal Transport:The Sinkhorn CDF and Quantile Operator