Compositional Semantic Parsing on Semi-Structured Tables

TL;DR

This paper introduces a new approach for semantic parsing on semi-structured tables, addressing both domain breadth and logical compositionality, and presents a new dataset of complex questions for evaluation.

Contribution

It proposes a logical-form driven parsing algorithm with strong typing constraints and releases a large dataset of complex questions on Wikipedia tables.

Findings

Significant improvements over natural baselines

Effective handling of broad domains and deep compositionality

New dataset with 22,033 complex questions

Abstract

Two important aspects of semantic parsing for question answering are the breadth of the knowledge source and the depth of logical compositionality. While existing work trades off one aspect for another, this paper simultaneously makes progress on both fronts through a new task: answering complex questions on semi-structured tables using question-answer pairs as supervision. The central challenge arises from two compounding factors: the broader domain results in an open-ended set of relations, and the deeper compositionality results in a combinatorial explosion in the space of logical forms. We propose a logical-form driven parsing algorithm guided by strong typing constraints and show that it obtains significant improvements over natural baselines. For evaluation, we created a new dataset of 22,033 complex questions on Wikipedia tables, which is made publicly available.