Domain Adaptation for Semantic Parsing

TL;DR

This paper introduces a two-stage domain adaptation framework for semantic parsing that effectively leverages limited target domain data by separating domain-invariant and domain-specific information, leading to improved performance.

Contribution

A novel coarse-to-fine semantic parser with domain discrimination and relevance attention for better domain adaptation in low-resource settings.

Findings

Outperforms several popular domain adaptation strategies.

Effectively exploits limited target data.

Captures domain differences with fewer target training instances.

Abstract

Recently, semantic parsing has attracted much attention in the community. Although many neural modeling efforts have greatly improved the performance, it still suffers from the data scarcity issue. In this paper, we propose a novel semantic parser for domain adaptation, where we have much fewer annotated data in the target domain compared to the source domain. Our semantic parser benefits from a two-stage coarse-to-fine framework, thus can provide different and accurate treatments for the two stages, i.e., focusing on domain invariant and domain specific information, respectively. In the coarse stage, our novel domain discrimination component and domain relevance attention encourage the model to learn transferable domain general structures. In the fine stage, the model is guided to concentrate on domain related details. Experiments on a benchmark dataset show that our method consistently outperforms several popular domain adaptation strategies. Additionally, we show that our model can well exploit limited target data to capture the difference between the source and target domain, even when the target domain has far fewer training instances.