paper
Geometry of Semantic Space: Comparative Study of Discrete and Continuous Models
paperactiveprovisional
geometry-of-semantic-space-comparative-study-of-discrete-and-continuous-models-6045f7ff·1 events·first seen 9d agoAliases: Geometry of Semantic Space: Comparative Study of Discrete and Continuous Models
Co-occurring entities
More like this (12)
Supervised Semantic Differentialdiscrete geometryRepresentational Similarity AnalysisContrastive-Difference CKA Reveals Concept-Specific Structural Alignment Across Language Model Architecturescontinuous diffusion language modelContinuous-Time Consistency ModelsLanguage Models Compare Quantities Using Number-specific and Unit-specific Heuristicscontrastive semantic alignmentPreserving Plasticity in Continual Learning via Dynamical IsometryMeasuring Semantic Progress in Multi-turn Dialogue via Information GainGeometric Action Modeldiscrete diffusion models
Recent events (1)
Comparative study of semantic geometry in transformer embeddings vs. graph-based lexical models
A preprint from arXiv compares the geometric and topological properties of transformer-based vector embeddings (CamemBERT) against lexical co-occurrence graphs for representing semantic structure. Applied to a French civic debate corpus, the study finds similar local topology but divergent global structure between the two approaches. The authors argue graph-based models offer more interpretable semantic organization and suggest graphs could guide neural architectures toward more stable, interpretable convergence.