arXiv (Cornell University) · 2018 · 95 citations · 5 references
ComputingComputer ScienceComputational LinguisticsMachine LearningNatural Language ProcessingGraph-based LearningHyperbolic GeometryLanguage ModelingMetric GeometryRiemannian GeometryWord EmbeddingsEmbedding LearningEmbedding-based SimilarityHyperbolic Word EmbeddingsHypernymy DetectionParallel TransportRiemannian MetricUnsupervised ClassificationWord Representation Learning
Words are not created equal. In fact, they form an aristocratic graph with a latent hierarchical structure that the next generation of unsupervised learned word embeddings should reveal. In this paper, justified by the notion of delta-hyperbolicity or tree-likeliness of a space, we propose to embed words in a Cartesian product of hyperbolic spaces which we theoretically connect to the Gaussian word embeddings and their Fisher geometry. This connection allows us to introduce a novel principled hypernymy score for word embeddings. Moreover, we adapt the well-known Glove algorithm to learn unsupervised word embeddings in this type of Riemannian manifolds. We further explain how to solve the analogy task using the Riemannian parallel transport that generalizes vector arithmetics to this new type of geometry. Empirically, based on extensive experiments, we prove that our embeddings, trained unsupervised, are the first to simultaneously outperform strong and popular baselines on the tasks of similarity, analogy and hypernymy detection. In particular, for word hypernymy, we obtain new state-of-the-art on fully unsupervised WBLESS classification accuracy.
5
Efficient Estimation of Word Representations in Vector Space
Tomáš Mikolov, Kai Chen, Greg S. Corrado et al. · arXiv (Cornell University) · 2013 · 11.7K citations · Full text
Riemannian Adaptive Optimization Methods.
Gary Bécigneul, Octavian-Eugen Ganea · arXiv (Cornell University) · 2018 · 68 citations · Full text