AnnoRetrieve: Structured Retrieval for Unstructured Documents
AnnoRetrieve introduces a new retrieval paradigm that replaces traditional vector embeddings with lightweight structured queries over automatically generated annotation schemas. Using SchemaBoot for schema induction and Structured Semantic Retrieval (SSR) for precise matching, AnnoRetrieve enables annotation-driven semantic retrieval without relying on LLM calls. Experiments on real-world datasets demonstrate that this approach significantly reduces LLM usage and retrieval costs while maintaining high accuracy.
Why it matters: AnnoRetrieve's annotation-driven approach could substantially reduce the computational and financial costs of large-scale document analysis, making precise retrieval more accessible and scalable.
Full story at: arXiv Information Retrieval ↗