Logo
ScienceStack
Table of Contents
Fetching ...
Sign In

AnnoRetrieve: Efficient Structured Retrieval for Unstructured Document Analysis

Teng Lin, Yuyu Luo, Nan Tang

Abstract

Unstructured documents dominate enterprise and web data, but their lack of explicit organization hinders precise information retrieval. Current mainstream retrieval methods, especially embedding-based vector search, rely on coarse-grained semantic similarity, incurring high computational cost and frequent LLM calls for post-processing. To address this critical issue, we propose AnnoRetrieve, a novel retrieval paradigm that shifts from embeddings to structured annotations, enabling precise, annotation-driven semantic retrieval. Our system replaces expensive vector comparisons with lightweight structured queries over automatically induced schemas, dramatically reducing LLM usage and overall cost. The system integrates two synergistic core innovations: SchemaBoot, which automatically generates document annotation schemas via multi-granularity pattern discovery and constraint-based optimization, laying a foundation for annotation-driven retrieval and eliminating manual schema design, and Structured Semantic Retrieval (SSR), the core retrieval engine, which unifies semantic understanding with structured query execution; by leveraging the annotated structure instead of vector embeddings, SSR achieves precise semantic matching, seamlessly completing attribute-value extraction, table generation, and progressive SQL-based reasoning without relying on LLM interventions. This annotation-driven paradigm overcomes the limitations of traditional vector-based methods with coarse-grained matching and heavy LLM dependency and graph-based methods with high computational overhead. Experiments on three real-world datasets confirm that AnnoRetrieve significantly lowers LLM call frequency and retrieval cost while maintaining high accuracy. AnnoRetrieve establishes a new paradigm for cost-effective, precise, and scalable document analysis through intelligent structuring.

AnnoRetrieve: Efficient Structured Retrieval for Unstructured Document Analysis

Abstract

Unstructured documents dominate enterprise and web data, but their lack of explicit organization hinders precise information retrieval. Current mainstream retrieval methods, especially embedding-based vector search, rely on coarse-grained semantic similarity, incurring high computational cost and frequent LLM calls for post-processing. To address this critical issue, we propose AnnoRetrieve, a novel retrieval paradigm that shifts from embeddings to structured annotations, enabling precise, annotation-driven semantic retrieval. Our system replaces expensive vector comparisons with lightweight structured queries over automatically induced schemas, dramatically reducing LLM usage and overall cost. The system integrates two synergistic core innovations: SchemaBoot, which automatically generates document annotation schemas via multi-granularity pattern discovery and constraint-based optimization, laying a foundation for annotation-driven retrieval and eliminating manual schema design, and Structured Semantic Retrieval (SSR), the core retrieval engine, which unifies semantic understanding with structured query execution; by leveraging the annotated structure instead of vector embeddings, SSR achieves precise semantic matching, seamlessly completing attribute-value extraction, table generation, and progressive SQL-based reasoning without relying on LLM interventions. This annotation-driven paradigm overcomes the limitations of traditional vector-based methods with coarse-grained matching and heavy LLM dependency and graph-based methods with high computational overhead. Experiments on three real-world datasets confirm that AnnoRetrieve significantly lowers LLM call frequency and retrieval cost while maintaining high accuracy. AnnoRetrieve establishes a new paradigm for cost-effective, precise, and scalable document analysis through intelligent structuring.

Paper Structure

This paper contains 28 sections, 9 equations, 2 figures, 3 tables.

Table of Contents

  1. Introduction
  2. Related Work
  3. Document Analysis for Structured Retrieval
  4. Query Systems over Heterogeneous Data
  5. System Design
  6. Overview
  7. Automated Schema Induction: SchemaBoot
  8. Multi-Granularity Semantic Extraction
  9. Schema Quality Evaluation
  10. Constrained Multi-Objective Optimization
  11. Structured Annotation Generation
  12. Structured Semantic Retrieval (SSR) Engine
  13. Semantic Parsing to Structured Query
  14. Core Retrieval with EXTRACT Function
  15. Algorithm and Latency Analysis
  16. ...and 13 more sections

Figures (2)

  • Figure 1: An architectural overview illustrating the flows from raw documents to structured knowledge and hybrid query processing in the current systems. Structured Semantic Retrieval achieves more precise retrieval by combining semantic understanding with structured reasoning
  • Figure 2: The pipeline of the AnnoRetrieve system, comprising a pre-annotation stage for schema-guided document annotation and a structured semantic retrieval stage for answering complex user queries. In the pre-annotation stage, Schemapboot generates and optimizes a multi-granularity schema, which is paired with models like GliNER2 to extract attribute-value pair annotations from raw documents. The retrieval framework translates natural language queries into SQL, filters documents via type and schema constraints, and constructs structured tables to enable hybrid semantic-structured reasoning, yielding precise answers to complex questions.