Model-based Interactive Semantic Parsing: A Unified Framework and A Text-to-SQL Case Study
This work addresses the challenge of improving semantic parsing accuracy and user confidence in interactive systems, with a focus on text-to-SQL applications.
The paper tackles the problem of interactive semantic parsing by proposing a unified framework where a model-based agent decides when and where to ask for human feedback, and demonstrates it on text-to-SQL datasets, achieving higher accuracy with less user feedback compared to existing methods.
As a promising paradigm, interactive semantic parsing has shown to improve both semantic parsing accuracy and user confidence in the results. In this paper, we propose a new, unified formulation of the interactive semantic parsing problem, where the goal is to design a model-based intelligent agent. The agent maintains its own state as the current predicted semantic parse, decides whether and where human intervention is needed, and generates a clarification question in natural language. A key part of the agent is a world model: it takes a percept (either an initial question or subsequent feedback from the user) and transitions to a new state. We then propose a simple yet remarkably effective instantiation of our framework, demonstrated on two text-to-SQL datasets (WikiSQL and Spider) with different state-of-the-art base semantic parsers. Compared to an existing interactive semantic parsing approach that treats the base parser as a black box, our approach solicits less user feedback but yields higher run-time accuracy.