HyperPersona is a hypergraph framework that jointly models document, sentence, and word levels of text via hyperedges and nodes, then uses a transformer graph encoder to predict Big Five personality traits from text alone.
Bert: Pre-training of deep bidirectional transformers for language understanding, 2019
3 Pith papers cite this work. Polarity classification is still indexing.
3
Pith papers citing it
representative citing papers
Nomic AI produced and open-sourced a reproducible 8192-context English text embedder that exceeds OpenAI Ada-002 and text-embedding-3-small performance on MTEB short-context and LoCo long-context benchmarks.
KairosHope is a new TSFM with dual-memory architecture (Titans short-term + CMS long-term) and hybrid head fusing tsfeatures, pre-trained via MTSM+InfoNCE on Monash then LP-FT adapted to UCR, claiming superior results on causal tasks like HAR.
citing papers explorer
-
HyperPersona: A Multi-Level Hypergraph Framework for Text-Based Automatic Personality Prediction
HyperPersona is a hypergraph framework that jointly models document, sentence, and word levels of text via hyperedges and nodes, then uses a transformer graph encoder to predict Big Five personality traits from text alone.
-
Nomic Embed: Training a Reproducible Long Context Text Embedder
Nomic AI produced and open-sourced a reproducible 8192-context English text embedder that exceeds OpenAI Ada-002 and text-embedding-3-small performance on MTEB short-context and LoCo long-context benchmarks.
-
KairosHope: A Next-Generation Time-Series Foundation Model for Specialized Classification via Dual-Memory Architecture
KairosHope is a new TSFM with dual-memory architecture (Titans short-term + CMS long-term) and hybrid head fusing tsfeatures, pre-trained via MTSM+InfoNCE on Monash then LP-FT adapted to UCR, claiming superior results on causal tasks like HAR.