Unsupervised Hierarchy Matching with Optimal Transport over Hyperbolic Spaces
arXiv:1911.02536
Abstract
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.
arXiv commentAISTATS 2020
References in corpus (12)
- Distributed Representations of Words and Phrases and their Compositionality
- A robust self-learning method for fully unsupervised cross-lingual mappings of word embeddings
- The Cramer Distance as a Solution to Biased Wasserstein Gradients
- Riemannian Adaptive Optimization Methods
- Sample Complexity of Sinkhorn divergences
- Interpolating between Optimal Transport and MMD using Sinkhorn Divergences
- Riemannian SVRG: Fast Stochastic Optimization on Riemannian Manifolds
- Neural Embeddings of Graphs in Hyperbolic Space
- Towards Optimal Transport with Global Invariances
- Gradient descent in hyperbolic space
- Fused Gromov-Wasserstein distance for structured objects: theoretical foundations and mathematical properties
- Introduction to Optimal Transport Theory