A Transition-based Algorithm for Unrestricted AMR Parsing

TL;DR

This paper introduces a greedy, non-projective transition-based parser for AMR graphs that effectively handles reentrancy and cycles, achieving competitive results close to the state of the art.

Contribution

It presents a novel transition system for unrestricted AMR parsing that natively manages reentrancy and cycles in a greedy, left-to-right manner.

Findings

Achieves a Smatch score of 64% on LDC2015E86.

Handles reentrant edges effectively.

Operates with a greedy, non-projective transition system.

Abstract

Non-projective parsing can be useful to handle cycles and reentrancy in AMR graphs. We explore this idea and introduce a greedy left-to-right non-projective transition-based parser. At each parsing configuration, an oracle decides whether to create a concept or whether to connect a pair of existing concepts. The algorithm handles reentrancy and arbitrary cycles natively, i.e. within the transition system itself. The model is evaluated on the LDC2015E86 corpus, obtaining results close to the state of the art, including a Smatch of 64%, and showing good behavior on reentrant edges.