EHRAG constructs structural hyperedges from sentence co-occurrence and semantic hyperedges from entity embedding clusters, then applies hybrid diffusion plus topic-aware PPR to retrieve top-k documents, outperforming baselines on four datasets with linear indexing cost and zero token overhead.
arXiv preprint (2023)
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
verdicts
UNVERDICTED 2representative citing papers
Graph metrics from similarity graphs plus active learning on cluster attributes produce a classifier that outperforms prior cluster repair methods on both clean and duplicate-containing datasets.
citing papers explorer
-
EHRAG: Bridging Semantic Gaps in Lightweight GraphRAG via Hybrid Hypergraph Construction and Retrieval
EHRAG constructs structural hyperedges from sentence co-occurrence and semantic hyperedges from entity embedding clusters, then applies hybrid diffusion plus topic-aware PPR to retrieve top-k documents, outperforming baselines on four datasets with linear indexing cost and zero token overhead.
-
Graph-based Active Learning for Entity Cluster Repair
Graph metrics from similarity graphs plus active learning on cluster attributes produce a classifier that outperforms prior cluster repair methods on both clean and duplicate-containing datasets.