An Incremental Parser for Abstract Meaning Representation

Abstract Meaning Representation (AMR) is a semantic representation for natural language that involves an easy annotation process, hence favoring the development of large datasets. It embeds traditional NLP tasks such as named entity recognition, semantic role labeling, word sense disambiguation and coreference resolution. We describe a transition system that parses the sentence left-to-right, in time linear in the size of the input. We further propose a test-suite that assesses specific subtasks that are helpful in comparing AMR parsers and show that our left-to-right parser is competitive with the state of the art on the LDC2015E86 dataset and it is superior in recovering reentrancies and handling polarity.