Cross-domain Generalization for AMR Parsing

TL;DR

This paper evaluates the domain dependence of AMR parsers, identifies key challenges in cross-domain generalization, and proposes methods to improve performance across different domains, demonstrating effectiveness on out-of-domain tests.

Contribution

It provides a comprehensive analysis of cross-domain challenges in AMR parsing and introduces approaches to mitigate domain distribution divergence.

Findings

Cross-domain AMR parsing is hindered by word and concept distribution shifts.

Proposed methods reduce domain divergence and improve out-of-domain performance.

Experimental results confirm the effectiveness of the proposed approaches.

Abstract

Abstract Meaning Representation (AMR) parsing aims to predict an AMR graph from textual input. Recently, there has been notable growth in AMR parsing performance. However, most existing work focuses on improving the performance in the specific domain, ignoring the potential domain dependence of AMR parsing systems. To address this, we extensively evaluate five representative AMR parsers on five domains and analyze challenges to cross-domain AMR parsing. We observe that challenges to cross-domain AMR parsing mainly arise from the distribution shift of words and AMR concepts. Based on our observation, we investigate two approaches to reduce the domain distribution divergence of text and AMR features, respectively. Experimental results on two out-of-domain test sets show the superiority of our method.