Inducing and Using Alignments for Transition-based AMR Parsing
This work addresses the need for simpler and more robust alignment methods in AMR parsing, which is incremental as it builds on existing transition-based approaches.
The paper tackled the problem of complex and uncertain node-to-word alignments in transition-based AMR parsing by proposing a neural aligner and integrating it with parser training, resulting in more accurate alignments and a new state-of-the-art for gold-only trained models on AMR3.0, matching silver-trained performance without beam search.
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.