PleaSQLarify: Visual Pragmatic Repair for Natural Language Database Querying
This addresses the issue of user intent mismatches in natural language interfaces for database querying, offering an incremental improvement through pragmatic repair.
The paper tackled the problem of ambiguity in natural language database queries by introducing pragmatic repair through a system called PleaSQLarify, which uses visual interaction for clarification, and in a study with twelve participants, it helped users recognize alternative interpretations and resolve ambiguity efficiently.
Natural language database interfaces broaden data access, yet they remain brittle under input ambiguity. Standard approaches often collapse uncertainty into a single query, offering little support for mismatches between user intent and system interpretation. We reframe this challenge through pragmatic inference: while users economize expressions, systems operate on priors over the action space that may not align with the users'. In this view, pragmatic repair -- incremental clarification through minimal interaction -- is a natural strategy for resolving underspecification. We present \textsc{PleaSQLarify}, which operationalizes pragmatic repair by structuring interaction around interpretable decision variables that enable efficient clarification. A visual interface complements this by surfacing the action space for exploration, requesting user disambiguation, and making belief updates traceable across turns. In a study with twelve participants, \textsc{PleaSQLarify} helped users recognize alternative interpretations and efficiently resolve ambiguity. Our findings highlight pragmatic repair as a design principle that fosters effective user control in natural language interfaces.