A Transition-based Algorithm for Unrestricted AMR Parsing
This addresses the problem of parsing complex semantic graphs for natural language processing researchers, though it is incremental as it builds on existing transition-based methods.
The paper tackles unrestricted AMR parsing by introducing a greedy left-to-right non-projective transition-based parser that handles reentrancy and cycles natively, achieving a Smatch score of 64% on the LDC2015E86 corpus, close to state-of-the-art results.
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.