Word Representations via Gaussian Embedding
arXiv:1412.6623
Abstract
Current work in lexical distributed representations maps each word to a point vector in low-dimensional space. Mapping instead to a density provides many interesting advantages, including better capturing uncertainty about a representation and its relationships, expressing asymmetries more naturally than dot product or cosine similarity, and enabling more expressive parameterization of decision boundaries. This paper advocates for density-based distributed embeddings and presents a method for learning representations in the space of Gaussian distributions. We compare performance on various word embedding benchmarks, investigate the ability of these embeddings to model entailment and other asymmetric relationships, and explore novel properties of the representation.
12 pages, published as conference paper at ICLR 2015
Cited by in corpus (15)
- TaxoCom: Topic Taxonomy Completion with Hierarchical Discovery of Novel Topic Clusters
- Gaussian Attention Model and Its Application to Knowledge Base Embedding and Question Answering
- Cognitive Database: A Step towards Endowing Relational Databases with Artificial Intelligence Capabilities
- Deep Learning for Learning Graph Representations
- Towards logical negation for compositional distributional semantics
- Personalised Federated Learning On Heterogeneous Feature Spaces
- Modeling Sequences as Distributions with Uncertainty for Sequential Recommendation
- Bootstrap Equilibrium and Probabilistic Speaker Representation Learning for Self-supervised Speaker Verification
- Mixture-of-tastes Models for Representing Users with Diverse Interests
- NEAT: A Label Noise-resistant Complementary Item Recommender System with Trustworthy Evaluation
- Zero-Shot Clinical Acronym Expansion via Latent Meaning Cells
- Convolutional Gaussian Embeddings for Personalized Recommendation with Uncertainty
- Learning Multi-Sense Word Distributions using Approximate Kullback-Leibler Divergence
- Bayesian Metric Learning for Uncertainty Quantification in Image Retrieval
- Learning Probabilistic Sentence Representations from Paraphrases