Spherical Text Embedding
arXiv:1911.01196
Abstract
Unsupervised text embedding has shown great power in a wide range of NLP tasks. While text embeddings are typically learned in the Euclidean space, directional similarity is often more effective in tasks such as word similarity and document clustering, which creates a gap between the training stage and usage stage of text embedding. To close this gap, we propose a spherical generative model based on which unsupervised word and paragraph embeddings are jointly learned. To learn text embeddings in the spherical space, we develop an efficient optimization algorithm with convergence guarantee based on Riemannian optimization. Our model enjoys high efficiency and achieves state-of-the-art performances on various text embedding tasks including word similarity and document clustering.
NeurIPS 2019. (Code: https://github.com/yumeng5/Spherical-Text-Embedding)
Cited by in corpus (17)
- Discriminative Topic Mining via Category-Name Guided Text Embedding
- AI4Bharat-IndicNLP Corpus: Monolingual Corpora and Word Embeddings for Indic Languages
- Relatively dominated representations
- Symmetric Spaces for Graph Embeddings: A Finsler-Riemannian Approach
- Weakly-Supervised Aspect-Based Sentiment Analysis via Joint Aspect-Sentiment Topic Embedding
- Separate and Attend in Personal Email Search
- Switch Spaces: Learning Product Spaces with Sparse Gating
- Hierarchical Metadata-Aware Document Categorization under Weak Supervision
- BiTe-GCN: A New GCN Architecture via BidirectionalConvolution of Topology and Features on Text-Rich Networks
- Multi-Facet Recommender Networks with Spherical Optimization
- Grand Challenges in Resilience: Autonomous System Resilience through Design and Runtime Measures
- Empirical Study of Named Entity Recognition Performance Using Distribution-aware Word Embedding
- SynSetExpan: An Iterative Framework for Joint Entity Set Expansion and Synonym Discovery
- MATCH: Metadata-Aware Text Classification in A Large Hierarchy
- Linear Classifiers in Product Space Forms
- Domain-adaptation of spherical embeddings
- Out-of-Category Document Identification Using Target-Category Names as Weak Supervision