Coupling Distributed and Symbolic Execution for Natural Language Queries

TL;DR

This paper introduces a hybrid approach combining distributed and symbolic execution methods to improve natural language querying of knowledge bases, achieving better accuracy, efficiency, and interpretability.

Contribution

It proposes a novel coupling of distributed and symbolic executors, pretraining the symbolic component with intermediate results from the distributed executor.

Findings

Significant accuracy improvements over individual executors

Enhanced learning and execution efficiency

High interpretability of the combined approach

Abstract

Building neural networks to query a knowledge base (a table) with natural language is an emerging research topic in deep learning. An executor for table querying typically requires multiple steps of execution because queries may have complicated structures. In previous studies, researchers have developed either fully distributed executors or symbolic executors for table querying. A distributed executor can be trained in an end-to-end fashion, but is weak in terms of execution efficiency and explicit interpretability. A symbolic executor is efficient in execution, but is very difficult to train especially at initial stages. In this paper, we propose to couple distributed and symbolic execution for natural language queries, where the symbolic executor is pretrained with the distributed executor's intermediate execution results in a step-by-step fashion. Experiments show that our approach significantly outperforms both distributed and symbolic executors, exhibiting high accuracy, high learning efficiency, high execution efficiency, and high interpretability.