An Incremental Parser for Abstract Meaning Representation

We describe an incremental parser for mapping input text into Abstract Meaning Representation (AMR) graphs. Our parser is based on a transition system for dependency parsing, and allows to incrementally parse the sentence into an AMR graph, if all other components that are needed by the parser (such as the part-of-speech tagger and the dependency parser) are incremental as well. We show that our parser has an advantage over state-of-the-art AMR parsers on several metrics.