Robust Subgraph Generation Improves Abstract Meaning Representation Parsing

TL;DR

This paper introduces a set of transformation-based actions for AMR node generation, enhancing robustness and improving parsing accuracy by 3 F1 points over previous methods.

Contribution

It proposes a novel set of actions for AMR subgraph generation that generalize better and are easier to learn, leading to improved parsing performance.

Findings

Achieved a 3 F1 point improvement on standard datasets.

The new approach outperforms previous state-of-the-art methods.

The method simplifies the learning process for AMR node generation.

Abstract

The Abstract Meaning Representation (AMR) is a representation for open-domain rich semantics, with potential use in fields like event extraction and machine translation. Node generation, typically done using a simple dictionary lookup, is currently an important limiting factor in AMR parsing. We propose a small set of actions that derive AMR subgraphs by transformations on spans of text, which allows for more robust learning of this stage. Our set of construction actions generalize better than the previous approach, and can be learned with a simple classifier. We improve on the previous state-of-the-art result for AMR parsing, boosting end-to-end performance by 3 F$_1$ on both the LDC2013E117 and LDC2014T12 datasets.