Papers with text indexing
Linking, Searching, and Visualizing Entities in Wikipedia (L18-1)
Copied to clipboard
| Challenge: | Existing systems to extract, index, search, and visualize entities in Wikipedia are not strings, but unique identifiers from Wikidata. |
| Approach: | They propose a system to extract, index, search, and visualize entities in Wikipedia . they use a document model to store linguistic annotations and a string matching engine . |
| Outcome: | The proposed system achieves CEAFm scores of 70.0 on English, 64.4 on Chinese, and 66.5 on Spanish. |
LightRAG: Simple and Fast Retrieval-Augmented Generation (2025.findings-emnlp)
Copied to clipboard
| Challenge: | Existing RAG systems rely on flat data representations and inadequate contextual awareness . lightRAG framework incorporates graph structures into text indexing and retrieval processes . |
| Approach: | LightRAG is a framework that integrates graph structures into text indexing and retrieval processes. |
| Outcome: | The proposed framework incorporates graph structures into text indexing and retrieval processes. |