Spherical Text Embedding
Not on the map. Why?
Abstract (arXiv)
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.
Key facts. Cited by 49 papers in the map (data through 14 Oct 2026). First posted on arXiv 4 Nov 2019.
Builds on
No reference list yet.
Built on by
Citing papers per year: 2021: 14; 2022: 9; 2023: 11; 2024: 1; 2025: 7; 2026: 7.
49 papers.
Sort:
By area:
- 2025RiemannGFM: Learning a Graph Foundation Model from Riemannian Geometrycited by 35
- 2022Topic Discovery via Latent Space Clustering of Pretrained Language Model Representationscited by 34
- 2021Pseudo-Riemannian Graph Convolutional Networkscited by 30
- 2022TaxoCom: Topic Taxonomy Completion with Hierarchical Discovery of Novel Topic Clusterscited by 30
- 2021Symmetric Spaces for Graph Embeddings: A Finsler-Riemannian Approachcited by 23
- 2021SphereFace Revived: Unifying Hyperspherical Face Recognitioncited by 23
- 2021MATCH: Metadata-Aware Text Classification in A Large Hierarchycited by 20
- 2023UUKG: Unified Urban Knowledge Graph Dataset for Urban Spatiotemporal Predictioncited by 20
- 2021Corpus-based Open-Domain Event Type Inductioncited by 18
- 2023vONTSS: vMF based semi-supervised neural topic modeling with optimal transportcited by 16
- 2022Dual-Geometric Space Embedding Model for Two-View Knowledge Graphscited by 12
- 2021Linear Classifiers in Product Space Formscited by 11
37 more
- 2023Vacaspati: A Diverse Corpus of Bangla Literaturecited by 10
- 2021MotifClass: Weakly Supervised Text Classification with Higher-order Metadata Informationcited by 9
- 2021Switch Spaces: Learning Product Spaces with Sparse Gatingcited by 6
- 2022On Hyperbolic Embeddings in 2D Object Detectioncited by 6
- 2022Text Transformations in Contrastive Self-Supervised Learning: A Reviewcited by 5
- 2023Principal Component Analysis in Space Formscited by 5
- 2022AMCAD: Adaptive Mixed-Curvature Representation based Advertisement Retrieval Systemcited by 4
- 2023Improving Heterogeneous Graph Learning with Weighted Mixed-Curvature Product Manifoldcited by 4
- 2023Topological Obstructions and How to Avoid Themcited by 4
- 2021Analysis and Prediction of NLP Models Via Task Embeddingscited by 3
- 2022ORDSIM: Ordinal Regression for E-Commerce Query Similarity Predictioncited by 3
- 2025Dynamic Bundling with Large Language Models for Zero-Shot Inference on Text-Attributed Graphscited by 3
- 2023Automatic Generation of Multiple-Choice Questionscited by 2
- 2023FMGNN: Fused Manifold Graph Neural Networkcited by 2
- 2023Normed Spaces for Graph Embeddingcited by 2
- 2025Directional Textual Inversion for Personalized Text-to-Image Generationcited by 2
- 2021Modelling Monotonic and Non-Monotonic Attribute Dependencies with Embeddings: A Theoretical Analysiscited by 1
- 2021Kernel distance measures for time series, random fields and other structured datacited by 1
- 2021Out-of-Category Document Identification Using Target-Category Names as Weak Supervisioncited by 1
- 2023A Simplified Framework for Contrastive Learning for Node Representationscited by 1
- 2023S2vNTM: Semi-supervised vMF Neural Topic Modelingcited by 1
- 2025Keep your distance: learning dispersed embeddings on mathbbSmcited by 1
- 2025Towards Non-Euclidean Foundation Models: Advancing AI Beyond Euclidean Frameworkscited by 1
- 2026Beyond Gaussian Bottlenecks: Topologically Aligned Encoding of Vision-Transformer Feature Spacescited by 1
- 2026Enabling KV Caching of Shared Prefix for Diffusion Language Modelscited by 1
- 2021Empirical Study of Named Entity Recognition Performance Using Distribution-aware Word Embeddingcited by 0
- 2021Domain-adaptation of spherical embeddingscited by 0
- 2022Weak Supervision in Analysis of News: Application to Economic Policy Uncertaintycited by 0
- 2022Generalised Spherical Text Embeddingcited by 0
- 2024Forecasting Application Counts in Talent Acquisition Platforms: Harnessing Multimodal Signals using LMscited by 0
- 2025PR-CapsNet: Pseudo-Riemannian Capsule Network with Adaptive Curvature Routing for Graph Learningcited by 0
- 2025Semantic Grounding Index: Geometric Bounds on Context Engagement in RAG Systemscited by 0
- 2026Are Emotions Arranged in a Circle? Geometric Analysis of Emotion Representations via Hyperspherical Contrastive Learningcited by 0
- 2026Sentence Curve Language Modelscited by 0
- 2026Pose Tracking with a Foundation Pose Model and an Ensemble Directional Kalman Filtercited by 0
- 2026Information-Geometric Optimization on Spherescited by 0
- 2026Learning What to Forget: Distributional Unlearning for LLM Representation Spacescited by 0
- 2026Learning What to Forget: Distributional Unlearning for LLM Representation Spaces30 Sep 2026
- 2026Information-Geometric Optimization on Spheres27 May 2026
- 2026Enabling KV Caching of Shared Prefix for Diffusion Language Models26 May 2026
- 2026Pose Tracking with a Foundation Pose Model and an Ensemble Directional Kalman Filter4 May 2026
- 2026Beyond Gaussian Bottlenecks: Topologically Aligned Encoding of Vision-Transformer Feature Spaces30 Apr 2026
- 2026Sentence Curve Language Models2 Feb 2026
- 2026Are Emotions Arranged in a Circle? Geometric Analysis of Emotion Representations via Hyperspherical Contrastive Learning10 Jan 2026
- 2025Semantic Grounding Index: Geometric Bounds on Context Engagement in RAG Systems15 Dec 2025
- 2025Directional Textual Inversion for Personalized Text-to-Image Generation15 Dec 2025
- 2025PR-CapsNet: Pseudo-Riemannian Capsule Network with Adaptive Curvature Routing for Graph Learning9 Dec 2025
- 2025Dynamic Bundling with Large Language Models for Zero-Shot Inference on Text-Attributed Graphs23 May 2025
- 2025Towards Non-Euclidean Foundation Models: Advancing AI Beyond Euclidean Frameworks20 May 2025
37 more
- 2025Keep your distance: learning dispersed embeddings on mathbbSm12 Feb 2025
- 2025RiemannGFM: Learning a Graph Foundation Model from Riemannian Geometry5 Feb 2025
- 2024Forecasting Application Counts in Talent Acquisition Platforms: Harnessing Multimodal Signals using LMs19 Nov 2024
- 2023Topological Obstructions and How to Avoid Them12 Dec 2023
- 2023Normed Spaces for Graph Embedding3 Dec 2023
- 2023Vacaspati: A Diverse Corpus of Bangla Literature11 Jul 2023
- 2023Improving Heterogeneous Graph Learning with Weighted Mixed-Curvature Product Manifold10 Jul 2023
- 2023S2vNTM: Semi-supervised vMF Neural Topic Modeling6 Jul 2023
- 2023vONTSS: vMF based semi-supervised neural topic modeling with optimal transport3 Jul 2023
- 2023UUKG: Unified Urban Knowledge Graph Dataset for Urban Spatiotemporal Prediction20 Jun 2023
- 2023A Simplified Framework for Contrastive Learning for Node Representations1 May 2023
- 2023FMGNN: Fused Manifold Graph Neural Network3 Apr 2023
- 2023Automatic Generation of Multiple-Choice Questions25 Mar 2023
- 2023Principal Component Analysis in Space Forms6 Jan 2023
- 2022Generalised Spherical Text Embedding30 Nov 2022
- 2022Dual-Geometric Space Embedding Model for Two-View Knowledge Graphs19 Sep 2022
- 2022Weak Supervision in Analysis of News: Application to Economic Policy Uncertainty10 Aug 2022
- 2022AMCAD: Adaptive Mixed-Curvature Representation based Advertisement Retrieval System28 Mar 2022
- 2022Text Transformations in Contrastive Self-Supervised Learning: A Review22 Mar 2022
- 2022On Hyperbolic Embeddings in 2D Object Detection15 Mar 2022
- 2022ORDSIM: Ordinal Regression for E-Commerce Query Similarity Prediction13 Mar 2022
- 2022Topic Discovery via Latent Space Clustering of Pretrained Language Model Representations9 Feb 2022
- 2022TaxoCom: Topic Taxonomy Completion with Hierarchical Discovery of Novel Topic Clusters18 Jan 2022
- 2021Analysis and Prediction of NLP Models Via Task Embeddings10 Dec 2021
- 2021Out-of-Category Document Identification Using Target-Category Names as Weak Supervision24 Nov 2021
- 2021MotifClass: Weakly Supervised Text Classification with Higher-order Metadata Information7 Nov 2021
- 2021Domain-adaptation of spherical embeddings1 Nov 2021
- 2021Kernel distance measures for time series, random fields and other structured data29 Sep 2021
- 2021SphereFace Revived: Unifying Hyperspherical Face Recognition12 Sep 2021
- 2021Corpus-based Open-Domain Event Type Induction7 Sep 2021
- 2021Empirical Study of Named Entity Recognition Performance Using Distribution-aware Word Embedding3 Sep 2021
- 2021Modelling Monotonic and Non-Monotonic Attribute Dependencies with Embeddings: A Theoretical Analysis28 Jun 2021
- 2021Symmetric Spaces for Graph Embeddings: A Finsler-Riemannian Approach9 Jun 2021
- 2021Pseudo-Riemannian Graph Convolutional Networks6 Jun 2021
- 2021Linear Classifiers in Product Space Forms19 Feb 2021
- 2021Switch Spaces: Learning Product Spaces with Sparse Gating17 Feb 2021
- 2021MATCH: Metadata-Aware Text Classification in A Large Hierarchy15 Feb 2021
- 2026Enabling KV Caching of Shared Prefix for Diffusion Language Modelscited by 1
- 2026Sentence Curve Language Modelscited by 0
- 2026Enabling KV Caching of Shared Prefix for Diffusion Language Models26 May 2026
- 2026Sentence Curve Language Models2 Feb 2026
- 2025RiemannGFM: Learning a Graph Foundation Model from Riemannian Geometrycited by 35
- 2022Topic Discovery via Latent Space Clustering of Pretrained Language Model Representationscited by 34
- 2021Pseudo-Riemannian Graph Convolutional Networkscited by 30
- 2022TaxoCom: Topic Taxonomy Completion with Hierarchical Discovery of Novel Topic Clusterscited by 30
- 2021Symmetric Spaces for Graph Embeddings: A Finsler-Riemannian Approachcited by 23
- 2021SphereFace Revived: Unifying Hyperspherical Face Recognitioncited by 23
- 2021MATCH: Metadata-Aware Text Classification in A Large Hierarchycited by 20
- 2023UUKG: Unified Urban Knowledge Graph Dataset for Urban Spatiotemporal Predictioncited by 20
- 2021Corpus-based Open-Domain Event Type Inductioncited by 18
- 2023vONTSS: vMF based semi-supervised neural topic modeling with optimal transportcited by 16
- 2022Dual-Geometric Space Embedding Model for Two-View Knowledge Graphscited by 12
- 2021Linear Classifiers in Product Space Formscited by 11
12 most cited of 44 All 44 (JSON)
- 2026Information-Geometric Optimization on Spheres27 May 2026
- 2026Pose Tracking with a Foundation Pose Model and an Ensemble Directional Kalman Filter4 May 2026
- 2026Are Emotions Arranged in a Circle? Geometric Analysis of Emotion Representations via Hyperspherical Contrastive Learning10 Jan 2026
- 2025Directional Textual Inversion for Personalized Text-to-Image Generation15 Dec 2025
- 2025PR-CapsNet: Pseudo-Riemannian Capsule Network with Adaptive Curvature Routing for Graph Learning9 Dec 2025
- 2025Dynamic Bundling with Large Language Models for Zero-Shot Inference on Text-Attributed Graphs23 May 2025
- 2025Towards Non-Euclidean Foundation Models: Advancing AI Beyond Euclidean Frameworks20 May 2025
- 2025Keep your distance: learning dispersed embeddings on mathbbSm12 Feb 2025
- 2025RiemannGFM: Learning a Graph Foundation Model from Riemannian Geometry5 Feb 2025
- 2024Forecasting Application Counts in Talent Acquisition Platforms: Harnessing Multimodal Signals using LMs19 Nov 2024
- 2023Topological Obstructions and How to Avoid Them12 Dec 2023
- 2023Normed Spaces for Graph Embedding3 Dec 2023
12 newest of 44 All 44 (JSON)