Inducing and Using Alignments for Transition-based AMR Parsing. (arXiv:2205.01464v1 [cs.CL])

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 …

amr arxiv parsing transition