AntTech
Oct 16, 2024 · Artificial Intelligence
Subgraph Retrieval Enhanced by Graph-Text Alignment for Commonsense Question Answering (SEPTA Framework)
The paper introduces the SEPTA framework, which converts knowledge graphs into a subgraph vector database and employs graph‑text alignment via bidirectional contrastive learning to improve subgraph retrieval and knowledge fusion for commonsense question answering, demonstrating strong performance across five benchmark datasets.
Knowledge GraphsSEPTAcommonsense QA
0 likes · 4 min read