Inducing and Using Alignments for Transition-based AMR Parsing

TL;DR

This paper introduces a neural aligner for AMR parsing that integrates alignment uncertainty into parser training, resulting in improved accuracy and state-of-the-art performance without complex pipelines or beam search.

Contribution

It proposes a neural alignment method and a joint training approach that incorporates alignment uncertainty, enhancing AMR parser performance.

Findings

More accurate alignments achieved

Better generalization from AMR2.0 to AMR3.0

State-of-the-art results on AMR3.0 without beam search

Abstract

Transition-based parsers for Abstract Meaning Representation (AMR) rely on node-to-word alignments. These alignments are learned separately from parser training and require a complex pipeline of rule-based components, pre-processing, and post-processing to satisfy domain-specific constraints. Parsers also train on a point-estimate of the alignment pipeline, neglecting the uncertainty due to the inherent ambiguity of alignment. In this work we explore two avenues for overcoming these limitations. First, we propose a neural aligner for AMR that learns node-to-word alignments without relying on complex pipelines. We subsequently explore a tighter integration of aligner and parser training by considering a distribution over oracle action sequences arising from aligner uncertainty. Empirical results show this approach leads to more accurate alignments and generalization better from the AMR2.0 to AMR3.0 corpora. We attain a new state-of-the art for gold-only trained models, matching silver-trained performance without the need for beam search on AMR3.0.