Model-based Interactive Semantic Parsing: A Unified Framework and A Text-to-SQL Case Study

TL;DR

This paper introduces a unified, model-based framework for interactive semantic parsing, exemplified through a Text-to-SQL case study, improving accuracy and reducing user feedback across datasets.

Contribution

It presents a novel, unified formulation for interactive semantic parsing with a world model, enhancing performance over existing black-box methods.

Findings

Higher run-time accuracy compared to existing methods

Solicits less user feedback while maintaining performance

Effective across different datasets and base parsers

Abstract

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.