SABER: A SQL-Compatible Semantic Document Processing System Based on Extended Relational Algebra

2025-08-29

AI Summary

Current semantic data processing systems lack a unified algebraic foundation, resulting in non-composable queries, limited optimizability, and absence of formal reasoning capabilities. To address this, we propose SABER—the first algebraic system designed specifically for semantic operations. SABER extends relational algebra to unify the processing of both structured and unstructured data, enabling formal verification, operator interoperability, and hybrid execution. Methodologically, it introduces semantic-aware operators, leverages large language models for semantic parsing, and provides a SQL-compatible declarative query interface. Experimental evaluation demonstrates that SABER supports flexible integration and efficient execution of operators from diverse semantic systems. Crucially, it preserves query composability and optimizability while significantly enhancing the maintainability and extensibility of semantic query systems.

Technology Category

• Data Mining & Knowledge Management: Intelligent Query Processing
• Natural Language Processing: Sentence-level Semantics, Textual Inference, etc.
• Constraint Satisfaction and Optimization: Satisfiability Modulo Theories

Application Category

• Semantics and Knowledge: Methods, algorithms and applications for the development of semantic models, knowledge graphs and other forms of structured data models with machine-interpretable semantics
• Search and Retrieval-Augmented AI: Web query analysis, representation and understanding
• Graph Algorithms and Modeling for the Web: Querying, indexing, and retrieval in Web-related graphs

Abstract

The emergence of large-language models (LLMs) has enabled a new class of semantic data processing systems (SDPSs) to support declarative queries against unstructured documents. Existing SDPSs are, however, lacking a unified algebraic foundation, making their queries difficult to compose, reason, and optimize. We propose a new semantic algebra, SABER (Semantic Algebra Based on Extended Relational algebra), opening the possibility of semantic operations' logical plan construction, optimization, and formal correctness guarantees. We further propose to implement SABER in a SQL-compatible syntax so that it natively supports mixed structured/unstructured data processing. With SABER, we showcase the feasibility of providing a unified interface for existing SDPSs so that it can effectively mix and match any semantically-compatible operator implementation from any SDPS, greatly enhancing SABER's applicability for community contributions.

Problem

• Lacking unified algebraic foundation for semantic data processing
• Difficulty in composing, reasoning, and optimizing semantic queries
• Need for SQL-compatible mixed structured/unstructured data processing

Innovation

• SQL-compatible semantic algebra for documents
• Extended relational algebra enabling logical optimization
• Unified interface supporting mixed structured/unstructured data