Learning Dependency-Based Compositional Semantics

TL;DR

This paper introduces dependency-based compositional semantics (DCS), a new formalism for semantic parsing that learns from question-answer pairs without needing annotated logical forms, achieving state-of-the-art results.

Contribution

The paper presents DCS, a novel semantic formalism that enables learning semantic parsers from question-answer pairs, reducing annotation costs and improving performance.

Findings

Outperforms existing state-of-the-art systems on semantic parsing benchmarks.

Learns semantic parsers using only question-answer pairs, no logical form annotations.

Uses a log-linear model with beam search and optimization for parameter estimation.

Abstract

Suppose we want to build a system that answers a natural language question by representing its semantics as a logical form and computing the answer given a structured database of facts. The core part of such a system is the semantic parser that maps questions to logical forms. Semantic parsers are typically trained from examples of questions annotated with their target logical forms, but this type of annotation is expensive. Our goal is to learn a semantic parser from question-answer pairs instead, where the logical form is modeled as a latent variable. Motivated by this challenging learning problem, we develop a new semantic formalism, dependency-based compositional semantics (DCS), which has favorable linguistic, statistical, and computational properties. We define a log-linear distribution over DCS logical forms and estimate the parameters using a simple procedure that alternates between beam search and numerical optimization. On two standard semantic parsing benchmarks, our system outperforms all existing state-of-the-art systems, despite using no annotated logical forms.