Feasible Plan Generation with Ambiguity-Boundedness in Cross-Model Query Processing

TL;DR

This paper introduces the Packed Plan Forest (PPF), a scalable structure that efficiently encodes all feasible logical plans for NL-to-DB queries, addressing ambiguity and infeasibility issues in cross-model query processing.

Contribution

The paper proposes the PPF structure with feasibility constraints, enabling efficient pruning of infeasible plans and supporting scalable NL-to-DB query planning across heterogeneous systems.

Findings

PPFs encode exponentially many ILPs with minimal overhead.

PPFs support polynomial size under bounded arity and vocabularies.

Experiments demonstrate PPFs' effectiveness in capturing feasible plans.

Abstract

Natural language (NL) interfaces to databases broaden access to heterogeneous data but often yield many ambiguous intermediate logical plans (ILPs) due to uncertain operator scope and predicate semantics. Many candidates are infeasible because of type mismatches, missing bindings, or engine-specific constraints. We address this challenge with \emph{feasibility constraints} for detecting local inconsistencies and introduce the Packed Plan Forest (PPF) a polynomially bounded structure that compactly encodes all feasible ILPs while pruning infeasible ones early. Extending packed parse forest ideas to multi-model settings, PPF supports efficient feasibility analysis through annotated operators. Formal results show polynomial size under bounded arity and annotation vocabularies, and experiments confirm that PPFs capture exponentially many ILPs with minimal overhead, establishing a scalable foundation for NL-to-DB query planning across heterogeneous systems